Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5102 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.7918. Min Act: -0.1700
Data Index: 1836995 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.7605. Min Act: -0.1700
Data Index: 6145261 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.6668. Min Act: -0.1700
Data Index: 6065334 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.6355. Min Act: -0.1700
Data Index: 2625494 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.6355. Min Act: -0.1700
Data Index: 8584449 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.5730. Min Act: -0.1700
Data Index: 7339741 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.5105. Min Act: -0.1700
Data Index: 3755617 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.4480. Min Act: -0.1700
Data Index: 6322878 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.4480. Min Act: -0.1700
Data Index: 4493485 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.4793. Min Act: -0.1700
Data Index: 370391 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.4168. Min Act: -0.1700
Data Index: 2013383 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.4168. Min Act: -0.1700
Data Index: 8031685 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.4168. Min Act: -0.1700
Data Index: 3682211 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.4168. Min Act: -0.1700
Data Index: 7503628 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.4480. Min Act: -0.1700
Data Index: 7004284 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.3855. Min Act: -0.1700
Data Index: 2959162 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.4480. Min Act: -0.1700
Data Index: 2264091 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.4168. Min Act: -0.1700
Data Index: 8031688 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.4168. Min Act: -0.1700
Data Index: 474455 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7918. Min Range: -4.7918
Max Act: 4.3855. Min Act: -0.1700
Data Index: 5840152 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19