Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2055 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.8079. Min Act: -0.1700
Data Index: 6231906 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.7760. Min Act: -0.1700
Data Index: 6033204 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.7282. Min Act: -0.1700
Data Index: 6651510 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.7282. Min Act: -0.1700
Data Index: 2126738 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.6641. Min Act: -0.1700
Data Index: 708849 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.5999. Min Act: -0.1700
Data Index: 5752091 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.5515. Min Act: -0.1700
Data Index: 5311904 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.5192. Min Act: -0.1700
Data Index: 3669452 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.5354. Min Act: -0.1700
Data Index: 2041245 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.5515. Min Act: -0.1699
Data Index: 4427519 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.5354. Min Act: -0.1700
Data Index: 6982075 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.5192. Min Act: -0.1700
Data Index: 3226606 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.5354. Min Act: -0.1700
Data Index: 1158614 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.5192. Min Act: -0.1697
Data Index: 7769410 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.4868. Min Act: -0.1700
Data Index: 7129362 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.5030. Min Act: -0.1700
Data Index: 2286655 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.4868. Min Act: -0.1700
Data Index: 4020512 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.4706. Min Act: -0.1699
Data Index: 6932920 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.4868. Min Act: -0.1700
Data Index: 4926836 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8079. Min Range: -2.8079
Max Act: 2.4706. Min Act: -0.1700
Data Index: 4494402 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19