Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4329 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5448. Min Range: -4.5448
Max Act: 4.5448. Min Act: -0.1700
Data Index: 1804932 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5448. Min Range: -4.5448
Max Act: 4.4198. Min Act: -0.1700
Data Index: 2125717 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5448. Min Range: -4.5448
Max Act: 4.2635. Min Act: -0.1700
Data Index: 26421 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5448. Min Range: -4.5448
Max Act: 4.2635. Min Act: -0.1700
Data Index: 7569443 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5448. Min Range: -4.5448
Max Act: 4.2948. Min Act: -0.1700
Data Index: 394979 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5448. Min Range: -4.5448
Max Act: 4.2010. Min Act: -0.1700
Data Index: 8739593 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5448. Min Range: -4.5448
Max Act: 4.0760. Min Act: -0.1700
Data Index: 6799499 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5448. Min Range: -4.5448
Max Act: 4.0447. Min Act: -0.1700
Data Index: 2407782 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5448. Min Range: -4.5448
Max Act: 4.0135. Min Act: -0.1700
Data Index: 394987 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5448. Min Range: -4.5448
Max Act: 4.0447. Min Act: -0.1700
Data Index: 365267 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5448. Min Range: -4.5448
Max Act: 4.0760. Min Act: -0.1700
Data Index: 4768141 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5448. Min Range: -4.5448
Max Act: 4.0447. Min Act: -0.1700
Data Index: 394983 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5448. Min Range: -4.5448
Max Act: 4.0135. Min Act: -0.1700
Data Index: 998863 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5448. Min Range: -4.5448
Max Act: 4.0135. Min Act: -0.1700
Data Index: 6066964 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5448. Min Range: -4.5448
Max Act: 3.9822. Min Act: -0.1700
Data Index: 2407778 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5448. Min Range: -4.5448
Max Act: 3.9822. Min Act: -0.1700
Data Index: 1398513 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5448. Min Range: -4.5448
Max Act: 3.9822. Min Act: -0.1700
Data Index: 179412 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5448. Min Range: -4.5448
Max Act: 3.9822. Min Act: -0.1700
Data Index: 8160989 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5448. Min Range: -4.5448
Max Act: 3.9822. Min Act: -0.1700
Data Index: 148003 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5448. Min Range: -4.5448
Max Act: 3.9822. Min Act: -0.1700
Data Index: 5488139 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19