Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1376 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.3236. Min Act: -0.1700
Data Index: 4489834 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.2765. Min Act: -0.1700
Data Index: 2221129 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.2765. Min Act: -0.1700
Data Index: 4856078 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.2451. Min Act: -0.1700
Data Index: 3051163 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.2137. Min Act: -0.1700
Data Index: 8261298 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.1980. Min Act: -0.1700
Data Index: 7093735 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.1665. Min Act: -0.1700
Data Index: 6404529 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.1665. Min Act: -0.1700
Data Index: 7597292 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.1665. Min Act: -0.1700
Data Index: 7067038 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.1508. Min Act: -0.1700
Data Index: 7061894 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.1508. Min Act: -0.1700
Data Index: 2997564 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.1508. Min Act: -0.1700
Data Index: 2546500 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.1508. Min Act: -0.1700
Data Index: 3757330 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.1350. Min Act: -0.1700
Data Index: 8544637 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.1350. Min Act: -0.1700
Data Index: 3859241 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.1350. Min Act: -0.1700
Data Index: 2066470 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.1350. Min Act: -0.1700
Data Index: 7776150 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.1350. Min Act: -0.1700
Data Index: 8151995 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.1193. Min Act: -0.1700
Data Index: 6389476 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3236. Min Range: -3.3236
Max Act: 3.1193. Min Act: -0.1700
Data Index: 3591454 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19