Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.4959. Min Range: -10.4959
Max Act: 10.4959. Min Act: -0.1700
Data Index: 499192 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4959. Min Range: -10.4959
Max Act: 10.3084. Min Act: -0.1700
Data Index: 7908903 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4959. Min Range: -10.4959
Max Act: 10.3084. Min Act: -0.1700
Data Index: 7976565 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4959. Min Range: -10.4959
Max Act: 10.2459. Min Act: -0.1700
Data Index: 6272842 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4959. Min Range: -10.4959
Max Act: 10.1834. Min Act: -0.1700
Data Index: 289949 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4959. Min Range: -10.4959
Max Act: 10.1834. Min Act: -0.1700
Data Index: 7908899 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4959. Min Range: -10.4959
Max Act: 9.9334. Min Act: -0.1700
Data Index: 4855017 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4959. Min Range: -10.4959
Max Act: 9.8709. Min Act: -0.1700
Data Index: 5231740 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4959. Min Range: -10.4959
Max Act: 9.8709. Min Act: -0.1700
Data Index: 8099285 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4959. Min Range: -10.4959
Max Act: 9.8709. Min Act: -0.1700
Data Index: 4938566 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4959. Min Range: -10.4959
Max Act: 9.8084. Min Act: -0.1700
Data Index: 8184942 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4959. Min Range: -10.4959
Max Act: 9.8084. Min Act: -0.1700
Data Index: 7847289 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4959. Min Range: -10.4959
Max Act: 9.8084. Min Act: -0.1700
Data Index: 3052474 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4959. Min Range: -10.4959
Max Act: 9.7459. Min Act: -0.1700
Data Index: 3403429 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4959. Min Range: -10.4959
Max Act: 9.8084. Min Act: -0.1700
Data Index: 2073211 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4959. Min Range: -10.4959
Max Act: 9.7459. Min Act: -0.1700
Data Index: 660599 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4959. Min Range: -10.4959
Max Act: 9.7459. Min Act: -0.1700
Data Index: 3792275 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4959. Min Range: -10.4959
Max Act: 9.7459. Min Act: -0.1700
Data Index: 6510774 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4959. Min Range: -10.4959
Max Act: 9.6834. Min Act: -0.1700
Data Index: 3611038 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4959. Min Range: -10.4959
Max Act: 9.6834. Min Act: -0.1700
Data Index: 3351082 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19