Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3274 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4742. Min Range: -7.4742
Max Act: 7.4742. Min Act: -0.1700
Data Index: 1708620 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4742. Min Range: -7.4742
Max Act: 7.0992. Min Act: -0.1700
Data Index: 2627856 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4742. Min Range: -7.4742
Max Act: 7.0679. Min Act: -0.1700
Data Index: 4011007 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4742. Min Range: -7.4742
Max Act: 7.0054. Min Act: -0.1700
Data Index: 693908 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4742. Min Range: -7.4742
Max Act: 6.9742. Min Act: -0.1700
Data Index: 6391432 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4742. Min Range: -7.4742
Max Act: 6.9429. Min Act: -0.1700
Data Index: 2377330 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4742. Min Range: -7.4742
Max Act: 6.8804. Min Act: -0.1700
Data Index: 7245598 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4742. Min Range: -7.4742
Max Act: 6.8492. Min Act: -0.1700
Data Index: 6587079 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4742. Min Range: -7.4742
Max Act: 6.8492. Min Act: -0.1700
Data Index: 2231494 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4742. Min Range: -7.4742
Max Act: 6.8179. Min Act: -0.1700
Data Index: 2395442 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4742. Min Range: -7.4742
Max Act: 6.8179. Min Act: -0.1700
Data Index: 4768950 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4742. Min Range: -7.4742
Max Act: 6.7867. Min Act: -0.1700
Data Index: 3602522 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4742. Min Range: -7.4742
Max Act: 6.7554. Min Act: -0.1700
Data Index: 4996800 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4742. Min Range: -7.4742
Max Act: 6.7867. Min Act: -0.1700
Data Index: 5987160 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4742. Min Range: -7.4742
Max Act: 6.7554. Min Act: -0.1700
Data Index: 2447633 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4742. Min Range: -7.4742
Max Act: 6.7242. Min Act: -0.1700
Data Index: 1212597 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4742. Min Range: -7.4742
Max Act: 6.7242. Min Act: -0.1700
Data Index: 2638101 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4742. Min Range: -7.4742
Max Act: 6.7242. Min Act: -0.1700
Data Index: 446479 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4742. Min Range: -7.4742
Max Act: 6.7242. Min Act: -0.1700
Data Index: 92567 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4742. Min Range: -7.4742
Max Act: 6.7242. Min Act: -0.1700
Data Index: 2099978 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19