Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.8271. Min Act: -0.1700
Data Index: 4987653 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.8271. Min Act: -0.1700
Data Index: 779700 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.7646. Min Act: -0.1700
Data Index: 2321052 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.4834. Min Act: -0.1700
Data Index: 7873379 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.4834. Min Act: -0.1700
Data Index: 8224485 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.3584. Min Act: -0.1700
Data Index: 7430871 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.3271. Min Act: -0.1700
Data Index: 972670 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.2959. Min Act: -0.1698
Data Index: 8090901 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.2646. Min Act: -0.1700
Data Index: 2321049 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.2646. Min Act: -0.1700
Data Index: 6276314 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.2021. Min Act: -0.1700
Data Index: 5152573 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.2333. Min Act: -0.1700
Data Index: 4717528 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.2021. Min Act: -0.1700
Data Index: 8194870 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.1708. Min Act: -0.1700
Data Index: 3604276 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.1708. Min Act: -0.1700
Data Index: 7316595 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.1083. Min Act: -0.1700
Data Index: 829088 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.1396. Min Act: -0.1683
Data Index: 2321048 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.1708. Min Act: -0.1700
Data Index: 972673 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.1396. Min Act: -0.1700
Data Index: 5790013 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8271. Min Range: -4.8271
Max Act: 4.1708. Min Act: -0.1698
Data Index: 2809672 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19