Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4485 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.6175. Min Act: -0.1700
Data Index: 7921969 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.6175. Min Act: -0.1700
Data Index: 2559979 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.5550. Min Act: -0.1700
Data Index: 2490107 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.5237. Min Act: -0.1700
Data Index: 5048476 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.4925. Min Act: -0.1700
Data Index: 2650462 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.4612. Min Act: -0.1700
Data Index: 971683 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.4612. Min Act: -0.1700
Data Index: 3868427 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.4300. Min Act: -0.1700
Data Index: 2433863 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.4300. Min Act: -0.1700
Data Index: 5368865 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.4300. Min Act: -0.1700
Data Index: 6683443 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.3987. Min Act: -0.1700
Data Index: 8725010 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.4300. Min Act: -0.1700
Data Index: 7818386 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.3987. Min Act: -0.1700
Data Index: 4351231 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.3987. Min Act: -0.1700
Data Index: 6359643 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.3987. Min Act: -0.1700
Data Index: 1468507 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.3987. Min Act: -0.1700
Data Index: 4265980 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.3987. Min Act: -0.1700
Data Index: 2469433 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.3987. Min Act: -0.1700
Data Index: 638664 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.3987. Min Act: -0.1700
Data Index: 6038158 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6175. Min Range: -4.6175
Max Act: 4.3987. Min Act: -0.1700
Data Index: 2356542 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19