Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2424 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.9345. Min Act: -0.1700
Data Index: 5024597 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.8095. Min Act: -0.1700
Data Index: 2011500 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.7782. Min Act: -0.1700
Data Index: 8417811 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.6845. Min Act: -0.1700
Data Index: 3469495 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.6845. Min Act: -0.1700
Data Index: 6264254 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.6532. Min Act: -0.1700
Data Index: 1503207 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.6220. Min Act: -0.1700
Data Index: 6264257 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.6220. Min Act: -0.1700
Data Index: 3233782 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.6220. Min Act: -0.1700
Data Index: 1972157 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.6220. Min Act: -0.1700
Data Index: 8606950 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.5282. Min Act: -0.1700
Data Index: 6493834 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.4970. Min Act: -0.1700
Data Index: 3591660 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.4970. Min Act: -0.1700
Data Index: 4904569 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.4970. Min Act: -0.1700
Data Index: 3634993 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.4970. Min Act: -0.1700
Data Index: 7279564 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.4970. Min Act: -0.1700
Data Index: 4353635 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.4657. Min Act: -0.1700
Data Index: 4927399 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.4657. Min Act: -0.1700
Data Index: 7393967 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.4345. Min Act: -0.1700
Data Index: 8502242 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.4032. Min Act: -0.1700
Data Index: 1266100 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19