Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3199 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.5029. Min Act: -0.1700
Data Index: 838948 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.4092. Min Act: -0.1700
Data Index: 5752102 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.4092. Min Act: -0.1700
Data Index: 5248163 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.3467. Min Act: -0.1700
Data Index: 3649735 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.3467. Min Act: -0.1700
Data Index: 6189338 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.2529. Min Act: -0.1700
Data Index: 4803402 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.2529. Min Act: -0.1700
Data Index: 3319776 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.2529. Min Act: -0.1700
Data Index: 7008892 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.1904. Min Act: -0.1700
Data Index: 1516352 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.1904. Min Act: -0.1700
Data Index: 8118892 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.1592. Min Act: -0.1700
Data Index: 6268144 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.1279. Min Act: -0.1700
Data Index: 3866153 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.1279. Min Act: -0.1700
Data Index: 4932343 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.1279. Min Act: -0.1700
Data Index: 7071485 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.1279. Min Act: -0.1700
Data Index: 5012133 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.0967. Min Act: -0.1700
Data Index: 7901489 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.0967. Min Act: -0.1700
Data Index: 6431863 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.0967. Min Act: -0.1700
Data Index: 8565270 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.1279. Min Act: -0.1700
Data Index: 5557390 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5029. Min Range: -6.5029
Max Act: 6.0654. Min Act: -0.1700
Data Index: 2384396 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19