Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6266 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.7844. Min Act: -0.1700
Data Index: 7614419 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.6281. Min Act: -0.1700
Data Index: 8771640 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.5031. Min Act: -0.1700
Data Index: 4703528 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.4406. Min Act: -0.1700
Data Index: 2341984 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.4406. Min Act: -0.1700
Data Index: 6667414 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.4406. Min Act: -0.1700
Data Index: 4306413 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.3781. Min Act: -0.1700
Data Index: 3594214 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.4094. Min Act: -0.1700
Data Index: 4801801 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.3469. Min Act: -0.1700
Data Index: 3329941 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.3469. Min Act: -0.1700
Data Index: 2261174 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.3156. Min Act: -0.1700
Data Index: 7082376 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.3156. Min Act: -0.1700
Data Index: 4381320 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.3156. Min Act: -0.1700
Data Index: 6777266 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.2844. Min Act: -0.1700
Data Index: 6657225 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.2844. Min Act: -0.1700
Data Index: 4665875 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.2844. Min Act: -0.1700
Data Index: 277971 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.2844. Min Act: -0.1700
Data Index: 4831199 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.2844. Min Act: -0.1700
Data Index: 1270675 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.2219. Min Act: -0.1700
Data Index: 4881018 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7844. Min Range: -6.7844
Max Act: 6.2531. Min Act: -0.1700
Data Index: 1958299 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19