Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2934 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.7786. Min Act: -0.1700
Data Index: 4817588 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.7307. Min Act: -0.1700
Data Index: 2919049 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.7148. Min Act: -0.1700
Data Index: 2954979 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.6828. Min Act: -0.1700
Data Index: 7933897 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.6828. Min Act: -0.1700
Data Index: 4560611 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.6828. Min Act: -0.1700
Data Index: 5572131 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.6667. Min Act: -0.1700
Data Index: 1130287 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.6507. Min Act: -0.1700
Data Index: 2147870 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.6346. Min Act: -0.1700
Data Index: 361897 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.6507. Min Act: -0.1700
Data Index: 361896 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.6346. Min Act: -0.1700
Data Index: 6610987 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.6186. Min Act: -0.1700
Data Index: 2887608 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.6025. Min Act: -0.1700
Data Index: 7073023 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.5864. Min Act: -0.1700
Data Index: 540021 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.5703. Min Act: -0.1700
Data Index: 4133927 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.5864. Min Act: -0.1700
Data Index: 2591102 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.5864. Min Act: -0.1700
Data Index: 6084315 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.6025. Min Act: -0.1700
Data Index: 4310331 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.5703. Min Act: -0.1700
Data Index: 2791465 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7786. Min Range: -2.7786
Max Act: 2.5703. Min Act: -0.1700
Data Index: 7402607 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19