Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2725 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.5945. Min Act: -0.1700
Data Index: 3498190 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.6258. Min Act: -0.1700
Data Index: 8816780 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.5945. Min Act: -0.1700
Data Index: 2522309 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.5633. Min Act: -0.1700
Data Index: 158768 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.5008. Min Act: -0.1700
Data Index: 7174265 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.5008. Min Act: -0.1700
Data Index: 6166988 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.4383. Min Act: -0.1700
Data Index: 4343210 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.4383. Min Act: -0.1700
Data Index: 7193502 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.4383. Min Act: -0.1700
Data Index: 6959270 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.4383. Min Act: -0.1700
Data Index: 868870 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.4383. Min Act: -0.1700
Data Index: 1292194 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.4383. Min Act: -0.1700
Data Index: 7243349 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.4070. Min Act: -0.1700
Data Index: 5134020 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.4383. Min Act: -0.1700
Data Index: 1765368 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.4383. Min Act: -0.1700
Data Index: 5811678 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.4070. Min Act: -0.1700
Data Index: 6886292 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.4070. Min Act: -0.1700
Data Index: 5097950 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.3758. Min Act: -0.1700
Data Index: 6465838 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.4070. Min Act: -0.1700
Data Index: 6431661 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6258. Min Range: -4.6258
Max Act: 4.4070. Min Act: -0.1700
Data Index: 6923712 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19