Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3552 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.9381. Min Act: -0.1700
Data Index: 1264451 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.8756. Min Act: -0.1700
Data Index: 898992 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.8131. Min Act: -0.1700
Data Index: 7022505 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.7194. Min Act: -0.1700
Data Index: 8120226 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.6256. Min Act: -0.1700
Data Index: 1026374 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.6256. Min Act: -0.1700
Data Index: 7692851 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.5944. Min Act: -0.1700
Data Index: 2384743 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.5006. Min Act: -0.1700
Data Index: 7295598 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.5319. Min Act: -0.1700
Data Index: 1051369 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.4694. Min Act: -0.1700
Data Index: 7203215 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.4694. Min Act: -0.1700
Data Index: 8217875 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.4694. Min Act: -0.1700
Data Index: 4384484 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.4694. Min Act: -0.1700
Data Index: 8574555 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.4381. Min Act: -0.1700
Data Index: 8444489 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.4069. Min Act: -0.1700
Data Index: 3104759 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.3756. Min Act: -0.1700
Data Index: 2034132 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.3756. Min Act: -0.1700
Data Index: 7479637 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.3756. Min Act: -0.1700
Data Index: 1194727 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.4069. Min Act: -0.1700
Data Index: 2843157 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9381. Min Range: -6.9381
Max Act: 6.4069. Min Act: -0.1700
Data Index: 1205191 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19