Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2534 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.7792. Min Act: -0.1700
Data Index: 3434161 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.6542. Min Act: -0.1700
Data Index: 1174383 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.6230. Min Act: -0.1700
Data Index: 5539984 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.5605. Min Act: -0.1700
Data Index: 3531121 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.5605. Min Act: -0.1700
Data Index: 7155893 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.5292. Min Act: -0.1700
Data Index: 8622187 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.5292. Min Act: -0.1700
Data Index: 4757494 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.4980. Min Act: -0.1700
Data Index: 657018 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.4980. Min Act: -0.1700
Data Index: 547885 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.4980. Min Act: -0.1700
Data Index: 5009139 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.4980. Min Act: -0.1700
Data Index: 3253063 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.4667. Min Act: -0.1700
Data Index: 1317477 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.4667. Min Act: -0.1700
Data Index: 8502929 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.4042. Min Act: -0.1700
Data Index: 249091 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.4355. Min Act: -0.1700
Data Index: 1470645 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.4355. Min Act: -0.1700
Data Index: 843294 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.4042. Min Act: -0.1700
Data Index: 1724166 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.4042. Min Act: -0.1700
Data Index: 2376235 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.4042. Min Act: -0.1700
Data Index: 4988180 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.4042. Min Act: -0.1700
Data Index: 7436622 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19