Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2866 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.7431. Min Act: -0.1700
Data Index: 4102385 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.6962. Min Act: -0.1700
Data Index: 1008758 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.6649. Min Act: -0.1700
Data Index: 6749440 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.6023. Min Act: -0.1700
Data Index: 1868206 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.5553. Min Act: -0.1700
Data Index: 2364029 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.5240. Min Act: -0.1700
Data Index: 8392013 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.5240. Min Act: -0.1700
Data Index: 4209531 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.5240. Min Act: -0.1700
Data Index: 8761361 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.5084. Min Act: -0.1700
Data Index: 614965 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.5084. Min Act: -0.1700
Data Index: 4362230 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.4927. Min Act: -0.1700
Data Index: 7954758 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.4770. Min Act: -0.1700
Data Index: 6438185 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.4614. Min Act: -0.1700
Data Index: 7629271 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.4614. Min Act: -0.1700
Data Index: 5350102 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.4614. Min Act: -0.1700
Data Index: 1775266 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.4457. Min Act: -0.1700
Data Index: 1443631 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.4457. Min Act: -0.1700
Data Index: 1096639 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.4143. Min Act: -0.1700
Data Index: 4199424 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.4300. Min Act: -0.1700
Data Index: 4393427 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7431. Min Range: -3.7431
Max Act: 3.4300. Min Act: -0.1700
Data Index: 8236856 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19