Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3864 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.5286. Min Act: -0.1700
Data Index: 4179132 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.3724. Min Act: -0.1700
Data Index: 1687687 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.3724. Min Act: -0.1700
Data Index: 8118807 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.3099. Min Act: -0.1700
Data Index: 6496026 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.3099. Min Act: -0.1700
Data Index: 3549617 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.2786. Min Act: -0.1700
Data Index: 887161 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.2786. Min Act: -0.1700
Data Index: 5380112 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.2474. Min Act: -0.1700
Data Index: 6959315 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.2474. Min Act: -0.1700
Data Index: 5948995 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.2474. Min Act: -0.1700
Data Index: 7694502 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.2474. Min Act: -0.1700
Data Index: 240406 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.2474. Min Act: -0.1700
Data Index: 3691799 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.2161. Min Act: -0.1700
Data Index: 2050756 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.2161. Min Act: -0.1700
Data Index: 8514365 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.2161. Min Act: -0.1700
Data Index: 8450271 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.2161. Min Act: -0.1700
Data Index: 2753062 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.1849. Min Act: -0.1700
Data Index: 4254105 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.1849. Min Act: -0.1700
Data Index: 3057244 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.1849. Min Act: -0.1700
Data Index: 4137334 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5286. Min Range: -5.5286
Max Act: 5.1849. Min Act: -0.1700
Data Index: 6065634 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19