Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3396 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5952. Min Range: -4.5952
Max Act: 4.5952. Min Act: -0.1700
Data Index: 3717117 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5952. Min Range: -4.5952
Max Act: 4.4077. Min Act: -0.1700
Data Index: 7847392 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5952. Min Range: -4.5952
Max Act: 4.2827. Min Act: -0.1700
Data Index: 3953440 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5952. Min Range: -4.5952
Max Act: 4.2514. Min Act: -0.1700
Data Index: 3717115 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5952. Min Range: -4.5952
Max Act: 4.0639. Min Act: -0.1700
Data Index: 2941779 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5952. Min Range: -4.5952
Max Act: 4.0639. Min Act: -0.1700
Data Index: 2963966 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5952. Min Range: -4.5952
Max Act: 4.0326. Min Act: -0.1700
Data Index: 5516539 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5952. Min Range: -4.5952
Max Act: 3.9701. Min Act: -0.1700
Data Index: 5791754 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5952. Min Range: -4.5952
Max Act: 3.9701. Min Act: -0.1700
Data Index: 5617298 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5952. Min Range: -4.5952
Max Act: 3.9701. Min Act: -0.1700
Data Index: 3727822 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5952. Min Range: -4.5952
Max Act: 4.0014. Min Act: -0.1700
Data Index: 4837039 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5952. Min Range: -4.5952
Max Act: 3.9389. Min Act: -0.1700
Data Index: 4888373 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5952. Min Range: -4.5952
Max Act: 3.9389. Min Act: -0.1700
Data Index: 6157789 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5952. Min Range: -4.5952
Max Act: 3.9076. Min Act: -0.1700
Data Index: 3547134 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5952. Min Range: -4.5952
Max Act: 3.9076. Min Act: -0.1700
Data Index: 8338259 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5952. Min Range: -4.5952
Max Act: 3.9076. Min Act: -0.1700
Data Index: 5063299 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5952. Min Range: -4.5952
Max Act: 3.9076. Min Act: -0.1700
Data Index: 6198489 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5952. Min Range: -4.5952
Max Act: 3.9076. Min Act: -0.1700
Data Index: 2042239 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5952. Min Range: -4.5952
Max Act: 3.9076. Min Act: -0.1700
Data Index: 4108072 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5952. Min Range: -4.5952
Max Act: 3.8763. Min Act: -0.1700
Data Index: 4541461 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19