Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2456 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0291. Min Range: -4.0291
Max Act: 4.0291. Min Act: -0.1700
Data Index: 8222346 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.9665. Min Act: -0.1700
Data Index: 5832179 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.9040. Min Act: -0.1700
Data Index: 5276088 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.8571. Min Act: -0.1700
Data Index: 8616493 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.8571. Min Act: -0.1700
Data Index: 7513194 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.8102. Min Act: -0.1700
Data Index: 1092690 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.8258. Min Act: -0.1700
Data Index: 4278346 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.8102. Min Act: -0.1700
Data Index: 7845024 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.7477. Min Act: -0.1700
Data Index: 5403474 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.7477. Min Act: -0.1700
Data Index: 4146857 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.7477. Min Act: -0.1700
Data Index: 7999020 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.7320. Min Act: -0.1700
Data Index: 7953531 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.7164. Min Act: -0.1700
Data Index: 8781664 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.7007. Min Act: -0.1700
Data Index: 258642 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.7007. Min Act: -0.1700
Data Index: 8351876 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.6851. Min Act: -0.1700
Data Index: 2295045 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.6694. Min Act: -0.1700
Data Index: 8700568 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.6851. Min Act: -0.1700
Data Index: 4117268 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.6694. Min Act: -0.1700
Data Index: 3629179 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0291. Min Range: -4.0291
Max Act: 3.6694. Min Act: -0.1700
Data Index: 3082488 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19