Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3546 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1188. Min Range: -4.1188
Max Act: 4.1188. Min Act: -0.1700
Data Index: 5323705 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1188. Min Range: -4.1188
Max Act: 4.0875. Min Act: -0.1700
Data Index: 6520372 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1188. Min Range: -4.1188
Max Act: 4.0562. Min Act: -0.1700
Data Index: 8180091 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1188. Min Range: -4.1188
Max Act: 4.0250. Min Act: -0.1700
Data Index: 524576 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1188. Min Range: -4.1188
Max Act: 4.0250. Min Act: -0.1700
Data Index: 3205129 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1188. Min Range: -4.1188
Max Act: 3.9937. Min Act: -0.1700
Data Index: 4152816 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1188. Min Range: -4.1188
Max Act: 3.9625. Min Act: -0.1700
Data Index: 7371125 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1188. Min Range: -4.1188
Max Act: 3.9625. Min Act: -0.1700
Data Index: 7510386 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1188. Min Range: -4.1188
Max Act: 3.9625. Min Act: -0.1700
Data Index: 1273706 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1188. Min Range: -4.1188
Max Act: 3.9312. Min Act: -0.1700
Data Index: 1680471 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1188. Min Range: -4.1188
Max Act: 3.9312. Min Act: -0.1700
Data Index: 8060060 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1188. Min Range: -4.1188
Max Act: 3.9312. Min Act: -0.1700
Data Index: 2443304 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1188. Min Range: -4.1188
Max Act: 3.8999. Min Act: -0.1700
Data Index: 3580952 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1188. Min Range: -4.1188
Max Act: 3.8999. Min Act: -0.1700
Data Index: 4909679 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1188. Min Range: -4.1188
Max Act: 3.8687. Min Act: -0.1700
Data Index: 7810060 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1188. Min Range: -4.1188
Max Act: 3.8687. Min Act: -0.1700
Data Index: 5428118 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1188. Min Range: -4.1188
Max Act: 3.8999. Min Act: -0.1700
Data Index: 6703060 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1188. Min Range: -4.1188
Max Act: 3.8687. Min Act: -0.1700
Data Index: 2372335 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1188. Min Range: -4.1188
Max Act: 3.8374. Min Act: -0.1700
Data Index: 5676992 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1188. Min Range: -4.1188
Max Act: 3.8374. Min Act: -0.1700
Data Index: 4847981 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19