Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.6228. Min Act: -0.1700
Data Index: 3073797 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.5603. Min Act: -0.1700
Data Index: 3073796 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.5290. Min Act: -0.1700
Data Index: 3073798 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.4978. Min Act: -0.1700
Data Index: 7533331 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.4665. Min Act: -0.1700
Data Index: 1946080 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.4040. Min Act: -0.1700
Data Index: 7689808 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.4040. Min Act: -0.1700
Data Index: 6920472 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.4040. Min Act: -0.1700
Data Index: 3073802 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.3728. Min Act: -0.1700
Data Index: 7039916 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.3728. Min Act: -0.1700
Data Index: 4653241 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.3728. Min Act: -0.1700
Data Index: 5788360 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.3728. Min Act: -0.1700
Data Index: 6920487 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.3415. Min Act: -0.1700
Data Index: 3933910 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.3415. Min Act: -0.1700
Data Index: 3108573 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.3415. Min Act: -0.1700
Data Index: 3073790 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.3415. Min Act: -0.1700
Data Index: 5657921 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.3415. Min Act: -0.1700
Data Index: 4873870 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.3415. Min Act: -0.1700
Data Index: 3108583 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.3103. Min Act: -0.1700
Data Index: 3558575 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6228. Min Range: -5.6228
Max Act: 5.3103. Min Act: -0.1700
Data Index: 5788356 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19