Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1978 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.4910. Min Act: -0.1700
Data Index: 8812486 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.4597. Min Act: -0.1700
Data Index: 1920192 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.4283. Min Act: -0.1700
Data Index: 3585853 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.4283. Min Act: -0.1700
Data Index: 6835893 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.4283. Min Act: -0.1700
Data Index: 2777739 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.3656. Min Act: -0.1700
Data Index: 3047024 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.3970. Min Act: -0.1700
Data Index: 4195673 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.3970. Min Act: -0.1700
Data Index: 5523266 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.3970. Min Act: -0.1700
Data Index: 2460026 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.3656. Min Act: -0.1700
Data Index: 2661266 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.3656. Min Act: -0.1700
Data Index: 2926382 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.3342. Min Act: -0.1700
Data Index: 5562634 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.3656. Min Act: -0.1700
Data Index: 5516988 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.3656. Min Act: -0.1700
Data Index: 1199182 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.3656. Min Act: -0.1700
Data Index: 5970524 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.3656. Min Act: -0.1700
Data Index: 4280505 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.3656. Min Act: -0.1700
Data Index: 6186761 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.3656. Min Act: -0.1700
Data Index: 5210530 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.3656. Min Act: -0.1700
Data Index: 2235312 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4910. Min Range: -3.4910
Max Act: 3.3656. Min Act: -0.1700
Data Index: 6291669 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19