Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 654 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.7467. Min Act: -0.1700
Data Index: 7073668 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.6842. Min Act: -0.1700
Data Index: 2870225 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.7154. Min Act: -0.1700
Data Index: 5761009 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.5592. Min Act: -0.1700
Data Index: 2091194 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.5279. Min Act: -0.1700
Data Index: 6285376 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.4967. Min Act: -0.1700
Data Index: 1476595 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.4967. Min Act: -0.1700
Data Index: 4430870 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.4029. Min Act: -0.1700
Data Index: 7147080 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.4029. Min Act: -0.1700
Data Index: 4972446 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.4029. Min Act: -0.1700
Data Index: 6335595 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.3717. Min Act: -0.1700
Data Index: 1651928 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.3404. Min Act: -0.1700
Data Index: 3103535 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.3092. Min Act: -0.1700
Data Index: 8713691 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.2154. Min Act: -0.1700
Data Index: 6673812 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.2467. Min Act: -0.1700
Data Index: 2957569 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.2154. Min Act: -0.1700
Data Index: 7379411 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.1842. Min Act: -0.1700
Data Index: 1928168 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.2154. Min Act: -0.1700
Data Index: 4259029 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.1842. Min Act: -0.1700
Data Index: 2687334 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.1529. Min Act: -0.1700
Data Index: 620415 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19