Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2601 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.7868. Min Act: -0.1700
Data Index: 8722715 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5681. Min Act: -0.1700
Data Index: 399662 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.4118. Min Act: -0.1700
Data Index: 4450152 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.2556. Min Act: -0.1700
Data Index: 7171303 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.1305. Min Act: -0.1700
Data Index: 4373292 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.1305. Min Act: -0.1700
Data Index: 3485244 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.1305. Min Act: -0.1700
Data Index: 8282828 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.0680. Min Act: -0.1700
Data Index: 2810196 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.0993. Min Act: -0.1700
Data Index: 7733689 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.0368. Min Act: -0.1700
Data Index: 5728284 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.0368. Min Act: -0.1700
Data Index: 3516348 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.0055. Min Act: -0.1700
Data Index: 831085 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.0055. Min Act: -0.1700
Data Index: 7209226 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.0055. Min Act: -0.1700
Data Index: 2760260 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7868. Min Range: -4.7868
Max Act: 3.9743. Min Act: -0.1700
Data Index: 1730825 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7868. Min Range: -4.7868
Max Act: 3.9743. Min Act: -0.1700
Data Index: 4043176 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7868. Min Range: -4.7868
Max Act: 3.9743. Min Act: -0.1700
Data Index: 1042618 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7868. Min Range: -4.7868
Max Act: 3.9430. Min Act: -0.1700
Data Index: 6663586 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7868. Min Range: -4.7868
Max Act: 3.9743. Min Act: -0.1700
Data Index: 3689471 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7868. Min Range: -4.7868
Max Act: 3.9430. Min Act: -0.1700
Data Index: 2177888 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19