Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4768 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1309. Min Range: -6.1309
Max Act: 6.1309. Min Act: -0.1700
Data Index: 3797391 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1309. Min Range: -6.1309
Max Act: 6.0372. Min Act: -0.1700
Data Index: 7280642 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1309. Min Range: -6.1309
Max Act: 6.0059. Min Act: -0.1700
Data Index: 7427596 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1309. Min Range: -6.1309
Max Act: 5.9434. Min Act: -0.1700
Data Index: 7556614 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1309. Min Range: -6.1309
Max Act: 5.9122. Min Act: -0.1700
Data Index: 3885678 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1309. Min Range: -6.1309
Max Act: 5.9434. Min Act: -0.1700
Data Index: 1418868 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1309. Min Range: -6.1309
Max Act: 5.8809. Min Act: -0.1700
Data Index: 7428591 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1309. Min Range: -6.1309
Max Act: 5.8497. Min Act: -0.1700
Data Index: 1984339 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1309. Min Range: -6.1309
Max Act: 5.8497. Min Act: -0.1700
Data Index: 5046847 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1309. Min Range: -6.1309
Max Act: 5.8497. Min Act: -0.1700
Data Index: 2386863 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1309. Min Range: -6.1309
Max Act: 5.8184. Min Act: -0.1700
Data Index: 7257168 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1309. Min Range: -6.1309
Max Act: 5.8184. Min Act: -0.1700
Data Index: 7257167 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1309. Min Range: -6.1309
Max Act: 5.7559. Min Act: -0.1700
Data Index: 3885679 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1309. Min Range: -6.1309
Max Act: 5.7559. Min Act: -0.1700
Data Index: 309184 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1309. Min Range: -6.1309
Max Act: 5.7247. Min Act: -0.1700
Data Index: 4471396 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1309. Min Range: -6.1309
Max Act: 5.7559. Min Act: -0.1700
Data Index: 8805330 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1309. Min Range: -6.1309
Max Act: 5.7247. Min Act: -0.1700
Data Index: 7257165 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1309. Min Range: -6.1309
Max Act: 5.7247. Min Act: -0.1700
Data Index: 7257169 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1309. Min Range: -6.1309
Max Act: 5.7247. Min Act: -0.1700
Data Index: 4103397 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1309. Min Range: -6.1309
Max Act: 5.7247. Min Act: -0.1700
Data Index: 1036604 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19