Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5657 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3471. Min Range: -6.3471
Max Act: 6.3471. Min Act: -0.1700
Data Index: 7256108 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3471. Min Range: -6.3471
Max Act: 6.2221. Min Act: -0.1700
Data Index: 8416944 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3471. Min Range: -6.3471
Max Act: 6.1284. Min Act: -0.1700
Data Index: 5922992 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3471. Min Range: -6.3471
Max Act: 6.1284. Min Act: -0.1700
Data Index: 6217040 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3471. Min Range: -6.3471
Max Act: 5.9409. Min Act: -0.1700
Data Index: 7333405 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3471. Min Range: -6.3471
Max Act: 5.9409. Min Act: -0.1700
Data Index: 6983612 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3471. Min Range: -6.3471
Max Act: 5.8784. Min Act: -0.1700
Data Index: 4874697 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3471. Min Range: -6.3471
Max Act: 5.8471. Min Act: -0.1700
Data Index: 5739580 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3471. Min Range: -6.3471
Max Act: 5.8159. Min Act: -0.1700
Data Index: 6226081 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3471. Min Range: -6.3471
Max Act: 5.8159. Min Act: -0.1700
Data Index: 7395161 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3471. Min Range: -6.3471
Max Act: 5.8159. Min Act: -0.1700
Data Index: 7634456 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3471. Min Range: -6.3471
Max Act: 5.8159. Min Act: -0.1700
Data Index: 7811280 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3471. Min Range: -6.3471
Max Act: 5.7846. Min Act: -0.1700
Data Index: 6180886 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3471. Min Range: -6.3471
Max Act: 5.7534. Min Act: -0.1700
Data Index: 3801153 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3471. Min Range: -6.3471
Max Act: 5.7534. Min Act: -0.1700
Data Index: 4000120 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3471. Min Range: -6.3471
Max Act: 5.7221. Min Act: -0.1700
Data Index: 4541561 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3471. Min Range: -6.3471
Max Act: 5.7221. Min Act: -0.1700
Data Index: 1796193 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3471. Min Range: -6.3471
Max Act: 5.6909. Min Act: -0.1700
Data Index: 4920238 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3471. Min Range: -6.3471
Max Act: 5.7534. Min Act: -0.1700
Data Index: 9169 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3471. Min Range: -6.3471
Max Act: 5.7221. Min Act: -0.1700
Data Index: 8013301 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19