Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3900 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.6016. Min Act: -0.1700
Data Index: 5305941 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.6016. Min Act: -0.1700
Data Index: 594454 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.5855. Min Act: -0.1700
Data Index: 402874 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.5694. Min Act: -0.1700
Data Index: 4406525 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.5694. Min Act: -0.1700
Data Index: 4818498 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.5532. Min Act: -0.1700
Data Index: 3744379 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.5532. Min Act: -0.1700
Data Index: 3932857 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.5532. Min Act: -0.1700
Data Index: 8653202 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.5371. Min Act: -0.1700
Data Index: 4761529 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.5209. Min Act: -0.1700
Data Index: 8675836 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.5371. Min Act: -0.1700
Data Index: 358409 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.5371. Min Act: -0.1700
Data Index: 2473106 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.5047. Min Act: -0.1700
Data Index: 7654308 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.5209. Min Act: -0.1700
Data Index: 3765184 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.5209. Min Act: -0.1700
Data Index: 7272065 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.5371. Min Act: -0.1700
Data Index: 3765185 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.5371. Min Act: -0.1700
Data Index: 118211 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.5209. Min Act: -0.1700
Data Index: 118207 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.5047. Min Act: -0.1700
Data Index: 4197655 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6016. Min Range: -2.6016
Max Act: 2.4885. Min Act: -0.1700
Data Index: 1269808 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19