Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5436 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.9860. Min Act: -0.1700
Data Index: 1067683 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.7047. Min Act: -0.1700
Data Index: 3826171 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.6110. Min Act: -0.1700
Data Index: 2446454 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.5485. Min Act: -0.1700
Data Index: 7702266 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.5172. Min Act: -0.1700
Data Index: 938365 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.4860. Min Act: -0.1700
Data Index: 6165588 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.4860. Min Act: -0.1700
Data Index: 1694137 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.4235. Min Act: -0.1700
Data Index: 7566516 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.3922. Min Act: -0.1700
Data Index: 1022146 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.4235. Min Act: -0.1700
Data Index: 5327453 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.3610. Min Act: -0.1700
Data Index: 8443193 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.3610. Min Act: -0.1700
Data Index: 4841254 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.3297. Min Act: -0.1700
Data Index: 6182889 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.2985. Min Act: -0.1700
Data Index: 7584796 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.2672. Min Act: -0.1700
Data Index: 5150914 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.2672. Min Act: -0.1700
Data Index: 1038869 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.2360. Min Act: -0.1700
Data Index: 6982410 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.2360. Min Act: -0.1700
Data Index: 1645614 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.2360. Min Act: -0.1700
Data Index: 8031918 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9860. Min Range: -6.9860
Max Act: 6.2360. Min Act: -0.1700
Data Index: 7431489 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19