Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4585 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.5652. Min Act: -0.1700
Data Index: 2941064 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.5330. Min Act: -0.1700
Data Index: 4368987 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.5168. Min Act: -0.1700
Data Index: 4203537 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.5006. Min Act: -0.1700
Data Index: 3849405 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.4844. Min Act: -0.1700
Data Index: 3482911 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.4844. Min Act: -0.1700
Data Index: 7620837 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.5006. Min Act: -0.1700
Data Index: 5001172 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.4844. Min Act: -0.1699
Data Index: 2461101 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.4844. Min Act: -0.1700
Data Index: 197457 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.4844. Min Act: -0.1700
Data Index: 5331134 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.4844. Min Act: -0.1700
Data Index: 7390996 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.4681. Min Act: -0.1700
Data Index: 2771658 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.4681. Min Act: -0.1700
Data Index: 3502871 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.4519. Min Act: -0.1700
Data Index: 3304840 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.4519. Min Act: -0.1700
Data Index: 8661296 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.4356. Min Act: -0.1700
Data Index: 3502873 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.4356. Min Act: -0.1700
Data Index: 810264 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.4193. Min Act: -0.1700
Data Index: 2420928 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.4193. Min Act: -0.1700
Data Index: 5108249 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5652. Min Range: -2.5652
Max Act: 2.4193. Min Act: -0.1700
Data Index: 4171725 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19