Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 660 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5521. Min Range: -8.5521
Max Act: 8.5521. Min Act: -0.1700
Data Index: 595134 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5521. Min Range: -8.5521
Max Act: 8.1146. Min Act: -0.1700
Data Index: 3129615 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5521. Min Range: -8.5521
Max Act: 7.8646. Min Act: -0.1700
Data Index: 4115362 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5521. Min Range: -8.5521
Max Act: 7.8959. Min Act: -0.1700
Data Index: 2796811 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5521. Min Range: -8.5521
Max Act: 7.8646. Min Act: -0.1700
Data Index: 3192330 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5521. Min Range: -8.5521
Max Act: 7.8334. Min Act: -0.1700
Data Index: 6727633 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5521. Min Range: -8.5521
Max Act: 7.8334. Min Act: -0.1700
Data Index: 5426624 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5521. Min Range: -8.5521
Max Act: 7.8334. Min Act: -0.1700
Data Index: 5966095 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5521. Min Range: -8.5521
Max Act: 7.8334. Min Act: -0.1700
Data Index: 6110516 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5521. Min Range: -8.5521
Max Act: 7.8021. Min Act: -0.1700
Data Index: 5838258 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5521. Min Range: -8.5521
Max Act: 7.8021. Min Act: -0.1700
Data Index: 1154077 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5521. Min Range: -8.5521
Max Act: 7.7084. Min Act: -0.1700
Data Index: 6601467 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5521. Min Range: -8.5521
Max Act: 7.7084. Min Act: -0.1700
Data Index: 3082753 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5521. Min Range: -8.5521
Max Act: 7.6771. Min Act: -0.1700
Data Index: 2560353 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5521. Min Range: -8.5521
Max Act: 7.6459. Min Act: -0.1700
Data Index: 7878299 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5521. Min Range: -8.5521
Max Act: 7.6459. Min Act: -0.1700
Data Index: 2988062 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5521. Min Range: -8.5521
Max Act: 7.5834. Min Act: -0.1700
Data Index: 8455768 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5521. Min Range: -8.5521
Max Act: 7.5834. Min Act: -0.1700
Data Index: 3966157 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5521. Min Range: -8.5521
Max Act: 7.5521. Min Act: -0.1700
Data Index: 8067108 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5521. Min Range: -8.5521
Max Act: 7.5209. Min Act: -0.1700
Data Index: 3626837 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19