Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3918 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.9860. Min Act: -0.1700
Data Index: 2740888 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.8610. Min Act: -0.1700
Data Index: 5299270 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.7360. Min Act: -0.1700
Data Index: 5611166 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.7360. Min Act: -0.1700
Data Index: 2026044 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.7360. Min Act: -0.1700
Data Index: 1499371 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.7360. Min Act: -0.1700
Data Index: 4808872 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.6735. Min Act: -0.1700
Data Index: 2522610 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.6735. Min Act: -0.1700
Data Index: 4422758 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.6735. Min Act: -0.1700
Data Index: 1152127 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.6735. Min Act: -0.1699
Data Index: 2497350 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.6110. Min Act: -0.1700
Data Index: 1149973 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.6110. Min Act: -0.1700
Data Index: 6866452 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.6110. Min Act: -0.1700
Data Index: 7419908 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.5485. Min Act: -0.1700
Data Index: 2229326 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.6110. Min Act: -0.1700
Data Index: 8362731 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.4860. Min Act: -0.1700
Data Index: 8741302 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.4860. Min Act: -0.1700
Data Index: 6975114 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.4860. Min Act: -0.1700
Data Index: 2934650 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.4235. Min Act: -0.1700
Data Index: 5763944 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9860. Min Range: -10.9860
Max Act: 10.4235. Min Act: -0.1699
Data Index: 7501466 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19