Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2441 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4231. Min Range: -9.4231
Max Act: 9.4231. Min Act: -0.1700
Data Index: 4950857 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4231. Min Range: -9.4231
Max Act: 9.3606. Min Act: -0.1700
Data Index: 54224 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4231. Min Range: -9.4231
Max Act: 9.2981. Min Act: -0.1700
Data Index: 734569 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4231. Min Range: -9.4231
Max Act: 9.2356. Min Act: -0.1700
Data Index: 5790747 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4231. Min Range: -9.4231
Max Act: 9.2981. Min Act: -0.1700
Data Index: 8738568 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4231. Min Range: -9.4231
Max Act: 9.2356. Min Act: -0.1700
Data Index: 3176663 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4231. Min Range: -9.4231
Max Act: 9.2356. Min Act: -0.1700
Data Index: 4120088 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4231. Min Range: -9.4231
Max Act: 9.1731. Min Act: -0.1700
Data Index: 7263757 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4231. Min Range: -9.4231
Max Act: 9.0481. Min Act: -0.1700
Data Index: 1052101 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4231. Min Range: -9.4231
Max Act: 8.9856. Min Act: -0.1700
Data Index: 5813695 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4231. Min Range: -9.4231
Max Act: 8.9856. Min Act: -0.1700
Data Index: 6438280 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4231. Min Range: -9.4231
Max Act: 8.9231. Min Act: -0.1700
Data Index: 6744643 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4231. Min Range: -9.4231
Max Act: 8.9231. Min Act: -0.1700
Data Index: 7908313 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4231. Min Range: -9.4231
Max Act: 8.9231. Min Act: -0.1700
Data Index: 2148508 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4231. Min Range: -9.4231
Max Act: 8.7981. Min Act: -0.1700
Data Index: 5732238 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4231. Min Range: -9.4231
Max Act: 8.8606. Min Act: -0.1700
Data Index: 5440233 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4231. Min Range: -9.4231
Max Act: 8.8606. Min Act: -0.1700
Data Index: 2761098 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4231. Min Range: -9.4231
Max Act: 8.7981. Min Act: -0.1700
Data Index: 4484336 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4231. Min Range: -9.4231
Max Act: 8.7981. Min Act: -0.1700
Data Index: 5295611 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4231. Min Range: -9.4231
Max Act: 8.7981. Min Act: -0.1700
Data Index: 117810 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19