Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1087 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1364. Min Range: -5.1364
Max Act: 5.1364. Min Act: -0.1700
Data Index: 1231043 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1364. Min Range: -5.1364
Max Act: 5.1364. Min Act: -0.1700
Data Index: 8459006 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1364. Min Range: -5.1364
Max Act: 5.0739. Min Act: -0.1700
Data Index: 7491572 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1364. Min Range: -5.1364
Max Act: 5.0426. Min Act: -0.1700
Data Index: 2790176 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1364. Min Range: -5.1364
Max Act: 5.0114. Min Act: -0.1700
Data Index: 2007756 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1364. Min Range: -5.1364
Max Act: 5.0114. Min Act: -0.1700
Data Index: 5215393 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1364. Min Range: -5.1364
Max Act: 5.0114. Min Act: -0.1700
Data Index: 517700 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1364. Min Range: -5.1364
Max Act: 5.0114. Min Act: -0.1700
Data Index: 1067832 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1364. Min Range: -5.1364
Max Act: 5.0114. Min Act: -0.1700
Data Index: 8819366 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1364. Min Range: -5.1364
Max Act: 4.9801. Min Act: -0.1700
Data Index: 6574455 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1364. Min Range: -5.1364
Max Act: 4.9801. Min Act: -0.1700
Data Index: 799637 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1364. Min Range: -5.1364
Max Act: 4.9801. Min Act: -0.1700
Data Index: 1353414 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1364. Min Range: -5.1364
Max Act: 4.9801. Min Act: -0.1700
Data Index: 369699 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1364. Min Range: -5.1364
Max Act: 4.9489. Min Act: -0.1700
Data Index: 832213 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1364. Min Range: -5.1364
Max Act: 4.9176. Min Act: -0.1700
Data Index: 4412478 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1364. Min Range: -5.1364
Max Act: 4.9176. Min Act: -0.1700
Data Index: 2400990 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1364. Min Range: -5.1364
Max Act: 4.8864. Min Act: -0.1700
Data Index: 8627141 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1364. Min Range: -5.1364
Max Act: 4.8239. Min Act: -0.1700
Data Index: 4847463 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1364. Min Range: -5.1364
Max Act: 4.8551. Min Act: -0.1700
Data Index: 3230663 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1364. Min Range: -5.1364
Max Act: 4.8551. Min Act: -0.1700
Data Index: 1735228 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19