Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1915 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.9396. Min Act: -0.1700
Data Index: 8291100 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.8459. Min Act: -0.1700
Data Index: 5872415 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.8459. Min Act: -0.1700
Data Index: 4372283 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.8146. Min Act: -0.1700
Data Index: 7449253 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.7834. Min Act: -0.1700
Data Index: 2437002 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.7521. Min Act: -0.1700
Data Index: 8275237 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.7209. Min Act: -0.1700
Data Index: 6716002 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.7209. Min Act: -0.1700
Data Index: 2319006 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.6584. Min Act: -0.1700
Data Index: 5531466 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.6896. Min Act: -0.1700
Data Index: 1299650 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.6584. Min Act: -0.1700
Data Index: 5319196 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.5959. Min Act: -0.1700
Data Index: 5668435 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.5646. Min Act: -0.1700
Data Index: 3870693 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.5334. Min Act: -0.1700
Data Index: 3098794 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.5334. Min Act: -0.1700
Data Index: 7014942 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.4709. Min Act: -0.1700
Data Index: 7063523 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.5021. Min Act: -0.1700
Data Index: 6687087 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.4396. Min Act: -0.1700
Data Index: 1247978 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.5021. Min Act: -0.1700
Data Index: 1723444 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9396. Min Range: -5.9396
Max Act: 5.4709. Min Act: -0.1700
Data Index: 4833527 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19