Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4809 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8226. Min Range: -8.8226
Max Act: 8.8226. Min Act: -0.1700
Data Index: 7384445 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8226. Min Range: -8.8226
Max Act: 8.6976. Min Act: -0.1700
Data Index: 5824623 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8226. Min Range: -8.8226
Max Act: 8.2601. Min Act: -0.1700
Data Index: 3090308 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8226. Min Range: -8.8226
Max Act: 8.0726. Min Act: -0.1700
Data Index: 7893185 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8226. Min Range: -8.8226
Max Act: 8.0726. Min Act: -0.1700
Data Index: 8611974 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8226. Min Range: -8.8226
Max Act: 8.0101. Min Act: -0.1700
Data Index: 2527642 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8226. Min Range: -8.8226
Max Act: 8.0413. Min Act: -0.1700
Data Index: 4465918 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8226. Min Range: -8.8226
Max Act: 7.9476. Min Act: -0.1700
Data Index: 5712423 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8226. Min Range: -8.8226
Max Act: 7.9163. Min Act: -0.1700
Data Index: 1970517 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8226. Min Range: -8.8226
Max Act: 7.9476. Min Act: -0.1700
Data Index: 4629437 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8226. Min Range: -8.8226
Max Act: 7.9163. Min Act: -0.1700
Data Index: 3939073 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8226. Min Range: -8.8226
Max Act: 7.8851. Min Act: -0.1700
Data Index: 7140236 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8226. Min Range: -8.8226
Max Act: 7.8538. Min Act: -0.1700
Data Index: 2892483 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8226. Min Range: -8.8226
Max Act: 7.8851. Min Act: -0.1700
Data Index: 5091627 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8226. Min Range: -8.8226
Max Act: 7.8226. Min Act: -0.1700
Data Index: 4723166 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8226. Min Range: -8.8226
Max Act: 7.7913. Min Act: -0.1700
Data Index: 1695819 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8226. Min Range: -8.8226
Max Act: 7.8226. Min Act: -0.1700
Data Index: 7473592 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8226. Min Range: -8.8226
Max Act: 7.8226. Min Act: -0.1700
Data Index: 667973 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8226. Min Range: -8.8226
Max Act: 7.7913. Min Act: -0.1700
Data Index: 7304164 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8226. Min Range: -8.8226
Max Act: 7.7913. Min Act: -0.1700
Data Index: 5645996 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19