Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2196 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4760. Min Act: -0.1700
Data Index: 1059628 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4760. Min Act: -0.1700
Data Index: 7024544 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4760. Min Act: -0.1700
Data Index: 5267412 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4672. Min Act: -0.1700
Data Index: 5858550 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4672. Min Act: -0.1700
Data Index: 6529056 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4496. Min Act: -0.1700
Data Index: 8178507 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4496. Min Act: -0.1700
Data Index: 7314505 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4408. Min Act: -0.1700
Data Index: 6047597 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4408. Min Act: -0.1700
Data Index: 2918647 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4408. Min Act: -0.1700
Data Index: 6138704 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4408. Min Act: -0.1700
Data Index: 2616550 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4320. Min Act: -0.1692
Data Index: 7156345 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4232. Min Act: -0.1700
Data Index: 2682208 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4320. Min Act: -0.1700
Data Index: 6227785 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4144. Min Act: -0.1700
Data Index: 3381593 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4144. Min Act: -0.1700
Data Index: 1600079 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4144. Min Act: -0.1699
Data Index: 6991853 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4144. Min Act: -0.1700
Data Index: 260032 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.4232. Min Act: -0.1695
Data Index: 1182290 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4760. Min Range: -1.4760
Max Act: 1.3792. Min Act: -0.1700
Data Index: 1384445 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19