Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5211 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0896. Min Range: -7.0896
Max Act: 7.0896. Min Act: -0.1700
Data Index: 34714 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0896. Min Range: -7.0896
Max Act: 7.0584. Min Act: -0.1700
Data Index: 5700652 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0896. Min Range: -7.0896
Max Act: 6.9646. Min Act: -0.1700
Data Index: 7952880 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0896. Min Range: -7.0896
Max Act: 6.9646. Min Act: -0.1700
Data Index: 8265461 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0896. Min Range: -7.0896
Max Act: 6.9334. Min Act: -0.1700
Data Index: 4378312 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0896. Min Range: -7.0896
Max Act: 6.9334. Min Act: -0.1700
Data Index: 4021235 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0896. Min Range: -7.0896
Max Act: 6.8084. Min Act: -0.1700
Data Index: 8429555 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0896. Min Range: -7.0896
Max Act: 6.7771. Min Act: -0.1700
Data Index: 957469 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0896. Min Range: -7.0896
Max Act: 6.7771. Min Act: -0.1700
Data Index: 3873532 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0896. Min Range: -7.0896
Max Act: 6.7771. Min Act: -0.1700
Data Index: 3289555 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0896. Min Range: -7.0896
Max Act: 6.7459. Min Act: -0.1700
Data Index: 911125 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0896. Min Range: -7.0896
Max Act: 6.7146. Min Act: -0.1700
Data Index: 6214694 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0896. Min Range: -7.0896
Max Act: 6.7459. Min Act: -0.1700
Data Index: 7968632 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0896. Min Range: -7.0896
Max Act: 6.7459. Min Act: -0.1700
Data Index: 8722394 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0896. Min Range: -7.0896
Max Act: 6.7459. Min Act: -0.1700
Data Index: 2100284 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0896. Min Range: -7.0896
Max Act: 6.7146. Min Act: -0.1700
Data Index: 1337726 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0896. Min Range: -7.0896
Max Act: 6.7146. Min Act: -0.1700
Data Index: 3705160 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0896. Min Range: -7.0896
Max Act: 6.7459. Min Act: -0.1700
Data Index: 3884284 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0896. Min Range: -7.0896
Max Act: 6.6834. Min Act: -0.1700
Data Index: 3371853 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0896. Min Range: -7.0896
Max Act: 6.6521. Min Act: -0.1700
Data Index: 531522 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19