Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 474 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.6902. Min Act: -0.1700
Data Index: 3802077 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.6277. Min Act: -0.1700
Data Index: 7084394 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.6277. Min Act: -0.1700
Data Index: 15769 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.5652. Min Act: -0.1700
Data Index: 6773662 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.5652. Min Act: -0.1700
Data Index: 3659204 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.5340. Min Act: -0.1700
Data Index: 1546509 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.5027. Min Act: -0.1700
Data Index: 3659201 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.5027. Min Act: -0.1700
Data Index: 4609712 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.4715. Min Act: -0.1700
Data Index: 4609714 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.4402. Min Act: -0.1700
Data Index: 6773661 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.4402. Min Act: -0.1700
Data Index: 1721348 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.4402. Min Act: -0.1700
Data Index: 15770 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.4090. Min Act: -0.1700
Data Index: 7366201 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.4090. Min Act: -0.1700
Data Index: 8215771 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.4090. Min Act: -0.1700
Data Index: 3534750 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.4090. Min Act: -0.1700
Data Index: 4238131 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.4090. Min Act: -0.1700
Data Index: 3534751 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.3777. Min Act: -0.1700
Data Index: 1721346 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.3777. Min Act: -0.1700
Data Index: 2675842 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6902. Min Range: -6.6902
Max Act: 6.3777. Min Act: -0.1700
Data Index: 3659203 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19