Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2621 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.9676. Min Act: -0.1700
Data Index: 7550150 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.9676. Min Act: -0.1700
Data Index: 3344244 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.9051. Min Act: -0.1700
Data Index: 3846629 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.8426. Min Act: -0.1700
Data Index: 327000 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.8114. Min Act: -0.1700
Data Index: 3028865 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.8114. Min Act: -0.1700
Data Index: 4963978 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.8114. Min Act: -0.1700
Data Index: 7205714 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.7801. Min Act: -0.1700
Data Index: 4056583 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.7801. Min Act: -0.1700
Data Index: 2243338 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.7489. Min Act: -0.1700
Data Index: 1823639 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.7489. Min Act: -0.1700
Data Index: 2618412 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.7489. Min Act: -0.1700
Data Index: 938122 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.7489. Min Act: -0.1700
Data Index: 577905 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.7489. Min Act: -0.1700
Data Index: 2314034 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.7176. Min Act: -0.1700
Data Index: 1709581 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.6864. Min Act: -0.1700
Data Index: 2036119 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.6864. Min Act: -0.1700
Data Index: 458076 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.6864. Min Act: -0.1700
Data Index: 6055356 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.6864. Min Act: -0.1700
Data Index: 386080 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9676. Min Range: -4.9676
Max Act: 4.6864. Min Act: -0.1700
Data Index: 2439167 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19