Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4353 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.5303. Min Act: -0.1700
Data Index: 4326535 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.3427. Min Act: -0.1700
Data Index: 7946276 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.3427. Min Act: -0.1700
Data Index: 519588 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.2490. Min Act: -0.1700
Data Index: 2154398 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.2177. Min Act: -0.1700
Data Index: 8632289 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.2177. Min Act: -0.1700
Data Index: 4889455 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.1865. Min Act: -0.1700
Data Index: 8302811 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.1865. Min Act: -0.1700
Data Index: 6734264 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.1552. Min Act: -0.1700
Data Index: 2130409 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.1552. Min Act: -0.1700
Data Index: 3210048 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.1552. Min Act: -0.1700
Data Index: 1495447 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.1552. Min Act: -0.1700
Data Index: 6722778 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.1552. Min Act: -0.1700
Data Index: 103454 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.1240. Min Act: -0.1700
Data Index: 2441673 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.1240. Min Act: -0.1700
Data Index: 714586 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.1240. Min Act: -0.1700
Data Index: 5760587 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.1240. Min Act: -0.1700
Data Index: 4283238 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.0927. Min Act: -0.1700
Data Index: 7246811 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.0927. Min Act: -0.1700
Data Index: 614701 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5303. Min Range: -4.5303
Max Act: 4.1240. Min Act: -0.1700
Data Index: 8733077 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19