Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4323 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4674. Min Range: -11.4674
Max Act: 11.4049. Min Act: -0.1700
Data Index: 3245720 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4674. Min Range: -11.4674
Max Act: 11.4674. Min Act: -0.1700
Data Index: 5172794 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4674. Min Range: -11.4674
Max Act: 11.0924. Min Act: -0.1700
Data Index: 4126519 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4674. Min Range: -11.4674
Max Act: 10.9674. Min Act: -0.1700
Data Index: 5093731 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4674. Min Range: -11.4674
Max Act: 10.7174. Min Act: -0.1700
Data Index: 4240796 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4674. Min Range: -11.4674
Max Act: 10.7174. Min Act: -0.1700
Data Index: 6232933 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4674. Min Range: -11.4674
Max Act: 10.7174. Min Act: -0.1700
Data Index: 5678187 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4674. Min Range: -11.4674
Max Act: 10.6549. Min Act: -0.1700
Data Index: 8413392 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4674. Min Range: -11.4674
Max Act: 10.6549. Min Act: -0.1700
Data Index: 314109 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4674. Min Range: -11.4674
Max Act: 10.6549. Min Act: -0.1700
Data Index: 5264919 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4674. Min Range: -11.4674
Max Act: 10.5924. Min Act: -0.1700
Data Index: 2306936 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4674. Min Range: -11.4674
Max Act: 10.5924. Min Act: -0.1700
Data Index: 5952876 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4674. Min Range: -11.4674
Max Act: 10.5299. Min Act: -0.1700
Data Index: 1492855 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4674. Min Range: -11.4674
Max Act: 10.5299. Min Act: -0.1700
Data Index: 6269542 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4674. Min Range: -11.4674
Max Act: 10.5299. Min Act: -0.1700
Data Index: 6864269 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4674. Min Range: -11.4674
Max Act: 10.4674. Min Act: -0.1700
Data Index: 6879113 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4674. Min Range: -11.4674
Max Act: 10.4674. Min Act: -0.1700
Data Index: 4985881 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4674. Min Range: -11.4674
Max Act: 10.4674. Min Act: -0.1700
Data Index: 828596 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4674. Min Range: -11.4674
Max Act: 10.4049. Min Act: -0.1700
Data Index: 4569795 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4674. Min Range: -11.4674
Max Act: 10.4049. Min Act: -0.1700
Data Index: 4417562 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19