Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2999 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.6538. Min Act: -0.1700
Data Index: 523141 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5895. Min Act: -0.1700
Data Index: 3950101 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5573. Min Act: -0.1700
Data Index: 6482013 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5573. Min Act: -0.1700
Data Index: 4398984 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5573. Min Act: -0.1700
Data Index: 7482504 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5411. Min Act: -0.1700
Data Index: 1163509 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5250. Min Act: -0.1700
Data Index: 5818102 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5250. Min Act: -0.1700
Data Index: 5060478 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5250. Min Act: -0.1700
Data Index: 6634292 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5250. Min Act: -0.1700
Data Index: 3757234 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5250. Min Act: -0.1700
Data Index: 5446306 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5250. Min Act: -0.1700
Data Index: 2065104 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5250. Min Act: -0.1700
Data Index: 5594894 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5250. Min Act: -0.1700
Data Index: 8762460 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5088. Min Act: -0.1700
Data Index: 3469432 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5088. Min Act: -0.1700
Data Index: 7345434 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.4764. Min Act: -0.1700
Data Index: 6302209 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.4926. Min Act: -0.1700
Data Index: 5044939 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.4926. Min Act: -0.1700
Data Index: 1231590 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.4764. Min Act: -0.1700
Data Index: 6028506 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19