Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1990 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0179. Min Range: -7.0179
Max Act: 7.0179. Min Act: -0.1700
Data Index: 426368 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.9554. Min Act: -0.1700
Data Index: 1996745 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.8929. Min Act: -0.1700
Data Index: 7552350 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.8617. Min Act: -0.1700
Data Index: 4756847 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.8304. Min Act: -0.1700
Data Index: 1042613 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.8304. Min Act: -0.1700
Data Index: 6582379 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.7992. Min Act: -0.1700
Data Index: 7054636 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.7992. Min Act: -0.1700
Data Index: 6063446 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.7992. Min Act: -0.1700
Data Index: 659501 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.7679. Min Act: -0.1700
Data Index: 3272355 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.7679. Min Act: -0.1700
Data Index: 5368837 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.7367. Min Act: -0.1700
Data Index: 5038556 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.7054. Min Act: -0.1700
Data Index: 6040668 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.7054. Min Act: -0.1700
Data Index: 5602485 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.7054. Min Act: -0.1700
Data Index: 6562916 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.7367. Min Act: -0.1700
Data Index: 6494532 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.7054. Min Act: -0.1700
Data Index: 2753501 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.6742. Min Act: -0.1700
Data Index: 3034116 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.6742. Min Act: -0.1700
Data Index: 2935330 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0179. Min Range: -7.0179
Max Act: 6.6742. Min Act: -0.1700
Data Index: 6127902 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19