Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6300 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2096. Min Range: -7.2096
Max Act: 7.2096. Min Act: -0.1700
Data Index: 5518198 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2096. Min Range: -7.2096
Max Act: 7.1784. Min Act: -0.1700
Data Index: 6209683 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2096. Min Range: -7.2096
Max Act: 7.1471. Min Act: -0.1700
Data Index: 5172243 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2096. Min Range: -7.2096
Max Act: 7.0846. Min Act: -0.1700
Data Index: 3881310 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2096. Min Range: -7.2096
Max Act: 7.1159. Min Act: -0.1700
Data Index: 8445515 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2096. Min Range: -7.2096
Max Act: 7.0534. Min Act: -0.1700
Data Index: 3675123 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2096. Min Range: -7.2096
Max Act: 7.0534. Min Act: -0.1700
Data Index: 1687478 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2096. Min Range: -7.2096
Max Act: 7.0534. Min Act: -0.1700
Data Index: 4164698 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2096. Min Range: -7.2096
Max Act: 7.0534. Min Act: -0.1700
Data Index: 3042395 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.9909. Min Act: -0.1700
Data Index: 678592 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2096. Min Range: -7.2096
Max Act: 7.0221. Min Act: -0.1700
Data Index: 5172577 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.9909. Min Act: -0.1700
Data Index: 3417040 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.9909. Min Act: -0.1700
Data Index: 3629533 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.9596. Min Act: -0.1700
Data Index: 4698518 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.9909. Min Act: -0.1700
Data Index: 8557174 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.9909. Min Act: -0.1700
Data Index: 2333326 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.9596. Min Act: -0.1700
Data Index: 6706825 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.9284. Min Act: -0.1700
Data Index: 5509806 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.9596. Min Act: -0.1700
Data Index: 3265424 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.9596. Min Act: -0.1700
Data Index: 4859094 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19