Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6195 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.3196. Min Act: -0.1700
Data Index: 4971204 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.2883. Min Act: -0.1700
Data Index: 4892187 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.3196. Min Act: -0.1700
Data Index: 3040811 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.2883. Min Act: -0.1700
Data Index: 3808454 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.2258. Min Act: -0.1700
Data Index: 2173831 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.2258. Min Act: -0.1700
Data Index: 7756399 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.1946. Min Act: -0.1700
Data Index: 3949353 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.1633. Min Act: -0.1700
Data Index: 1144984 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.1946. Min Act: -0.1700
Data Index: 4460964 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.1946. Min Act: -0.1700
Data Index: 1660794 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.1946. Min Act: -0.1700
Data Index: 1464420 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.1946. Min Act: -0.1700
Data Index: 7216868 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.1321. Min Act: -0.1700
Data Index: 8798617 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.1321. Min Act: -0.1700
Data Index: 587230 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.1633. Min Act: -0.1700
Data Index: 6058554 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.1321. Min Act: -0.1700
Data Index: 3404477 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.1321. Min Act: -0.1700
Data Index: 33376 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.1321. Min Act: -0.1700
Data Index: 1083530 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.1321. Min Act: -0.1700
Data Index: 4974201 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.1008. Min Act: -0.1700
Data Index: 6537121 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19