Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3040 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5570. Min Range: -9.5570
Max Act: 9.5570. Min Act: -0.1700
Data Index: 2658369 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5570. Min Range: -9.5570
Max Act: 9.4945. Min Act: -0.1700
Data Index: 7976661 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5570. Min Range: -9.5570
Max Act: 9.3070. Min Act: -0.1700
Data Index: 6960919 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5570. Min Range: -9.5570
Max Act: 9.3070. Min Act: -0.1700
Data Index: 71230 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5570. Min Range: -9.5570
Max Act: 9.2445. Min Act: -0.1700
Data Index: 7426573 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5570. Min Range: -9.5570
Max Act: 9.1195. Min Act: -0.1700
Data Index: 3327258 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5570. Min Range: -9.5570
Max Act: 9.1820. Min Act: -0.1700
Data Index: 631860 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5570. Min Range: -9.5570
Max Act: 9.0570. Min Act: -0.1700
Data Index: 4001815 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5570. Min Range: -9.5570
Max Act: 8.9945. Min Act: -0.1700
Data Index: 329993 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5570. Min Range: -9.5570
Max Act: 8.8695. Min Act: -0.1700
Data Index: 3465525 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5570. Min Range: -9.5570
Max Act: 8.8070. Min Act: -0.1700
Data Index: 6995245 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5570. Min Range: -9.5570
Max Act: 8.8070. Min Act: -0.1700
Data Index: 4614646 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5570. Min Range: -9.5570
Max Act: 8.7445. Min Act: -0.1700
Data Index: 4998401 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5570. Min Range: -9.5570
Max Act: 8.8070. Min Act: -0.1700
Data Index: 7036788 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5570. Min Range: -9.5570
Max Act: 8.6820. Min Act: -0.1700
Data Index: 591245 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5570. Min Range: -9.5570
Max Act: 8.6820. Min Act: -0.1700
Data Index: 6932364 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5570. Min Range: -9.5570
Max Act: 8.6820. Min Act: -0.1700
Data Index: 754827 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5570. Min Range: -9.5570
Max Act: 8.6820. Min Act: -0.1700
Data Index: 7793243 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5570. Min Range: -9.5570
Max Act: 8.6820. Min Act: -0.1700
Data Index: 3121767 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5570. Min Range: -9.5570
Max Act: 8.6195. Min Act: -0.1700
Data Index: 3573463 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19