Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 69 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4394. Min Range: -7.4394
Max Act: 7.4394. Min Act: -0.1700
Data Index: 3474899 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4394. Min Range: -7.4394
Max Act: 7.4394. Min Act: -0.1700
Data Index: 6188026 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4394. Min Range: -7.4394
Max Act: 7.3769. Min Act: -0.1700
Data Index: 5420995 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4394. Min Range: -7.4394
Max Act: 7.3456. Min Act: -0.1700
Data Index: 7289985 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4394. Min Range: -7.4394
Max Act: 7.2831. Min Act: -0.1700
Data Index: 4821534 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4394. Min Range: -7.4394
Max Act: 7.2831. Min Act: -0.1700
Data Index: 3164711 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4394. Min Range: -7.4394
Max Act: 7.2206. Min Act: -0.1700
Data Index: 4271064 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4394. Min Range: -7.4394
Max Act: 7.2206. Min Act: -0.1700
Data Index: 3206213 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4394. Min Range: -7.4394
Max Act: 7.2206. Min Act: -0.1700
Data Index: 5802146 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4394. Min Range: -7.4394
Max Act: 7.2519. Min Act: -0.1700
Data Index: 3746615 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4394. Min Range: -7.4394
Max Act: 7.1581. Min Act: -0.1700
Data Index: 1937439 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4394. Min Range: -7.4394
Max Act: 7.0644. Min Act: -0.1700
Data Index: 1579564 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4394. Min Range: -7.4394
Max Act: 7.0644. Min Act: -0.1700
Data Index: 4346364 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4394. Min Range: -7.4394
Max Act: 7.0644. Min Act: -0.1700
Data Index: 6156360 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4394. Min Range: -7.4394
Max Act: 7.0331. Min Act: -0.1700
Data Index: 3806979 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4394. Min Range: -7.4394
Max Act: 7.0019. Min Act: -0.1700
Data Index: 7298894 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4394. Min Range: -7.4394
Max Act: 6.9706. Min Act: -0.1700
Data Index: 3234189 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4394. Min Range: -7.4394
Max Act: 6.9706. Min Act: -0.1700
Data Index: 911734 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4394. Min Range: -7.4394
Max Act: 6.9394. Min Act: -0.1700
Data Index: 1257276 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4394. Min Range: -7.4394
Max Act: 6.9706. Min Act: -0.1700
Data Index: 418819 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19