Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4235 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.3090. Min Range: -9.3090
Max Act: 9.3090. Min Act: -0.1700
Data Index: 2027110 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3090. Min Range: -9.3090
Max Act: 9.3090. Min Act: -0.1700
Data Index: 1503515 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3090. Min Range: -9.3090
Max Act: 9.1840. Min Act: -0.1700
Data Index: 7748438 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3090. Min Range: -9.3090
Max Act: 9.0590. Min Act: -0.1700
Data Index: 2392230 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3090. Min Range: -9.3090
Max Act: 9.1215. Min Act: -0.1700
Data Index: 4308834 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3090. Min Range: -9.3090
Max Act: 9.0590. Min Act: -0.1700
Data Index: 466484 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3090. Min Range: -9.3090
Max Act: 9.0590. Min Act: -0.1700
Data Index: 7726912 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3090. Min Range: -9.3090
Max Act: 9.0590. Min Act: -0.1700
Data Index: 8601138 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3090. Min Range: -9.3090
Max Act: 8.9965. Min Act: -0.1700
Data Index: 3005381 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3090. Min Range: -9.3090
Max Act: 8.9340. Min Act: -0.1700
Data Index: 4901235 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3090. Min Range: -9.3090
Max Act: 8.9965. Min Act: -0.1700
Data Index: 5244590 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3090. Min Range: -9.3090
Max Act: 8.9965. Min Act: -0.1700
Data Index: 1461465 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3090. Min Range: -9.3090
Max Act: 8.9965. Min Act: -0.1700
Data Index: 8698508 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3090. Min Range: -9.3090
Max Act: 8.9340. Min Act: -0.1700
Data Index: 5343835 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3090. Min Range: -9.3090
Max Act: 8.9340. Min Act: -0.1700
Data Index: 3296157 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3090. Min Range: -9.3090
Max Act: 8.9340. Min Act: -0.1700
Data Index: 2702694 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3090. Min Range: -9.3090
Max Act: 8.8715. Min Act: -0.1700
Data Index: 20602 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3090. Min Range: -9.3090
Max Act: 8.8715. Min Act: -0.1700
Data Index: 7524800 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3090. Min Range: -9.3090
Max Act: 8.8715. Min Act: -0.1700
Data Index: 4117632 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3090. Min Range: -9.3090
Max Act: 8.8715. Min Act: -0.1700
Data Index: 3193096 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19