Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2283 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.7911. Min Act: -0.1700
Data Index: 5706474 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.7286. Min Act: -0.1700
Data Index: 2895980 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.7286. Min Act: -0.1700
Data Index: 6914700 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.7286. Min Act: -0.1700
Data Index: 905748 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.7286. Min Act: -0.1700
Data Index: 3741915 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.6973. Min Act: -0.1700
Data Index: 7759858 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.7286. Min Act: -0.1700
Data Index: 89761 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.6973. Min Act: -0.1700
Data Index: 5681233 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.6973. Min Act: -0.1700
Data Index: 8830963 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.6973. Min Act: -0.1700
Data Index: 5569402 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.6973. Min Act: -0.1700
Data Index: 4672593 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.6973. Min Act: -0.1700
Data Index: 4253563 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.6973. Min Act: -0.1700
Data Index: 6023962 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.6973. Min Act: -0.1700
Data Index: 4138086 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.6973. Min Act: -0.1700
Data Index: 7210592 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.6973. Min Act: -0.1700
Data Index: 7018880 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.6973. Min Act: -0.1700
Data Index: 6310287 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.6973. Min Act: -0.1700
Data Index: 6064626 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.6660. Min Act: -0.1700
Data Index: 1263520 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7911. Min Range: -3.7911
Max Act: 3.6660. Min Act: -0.1700
Data Index: 453886 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19