Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5013 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1381. Min Range: -6.1381
Max Act: 6.1381. Min Act: -0.1700
Data Index: 2396348 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1381. Min Range: -6.1381
Max Act: 6.0756. Min Act: -0.1700
Data Index: 3480284 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1381. Min Range: -6.1381
Max Act: 6.0131. Min Act: -0.1700
Data Index: 348363 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1381. Min Range: -6.1381
Max Act: 5.9819. Min Act: -0.1700
Data Index: 3480272 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1381. Min Range: -6.1381
Max Act: 5.9194. Min Act: -0.1700
Data Index: 348346 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1381. Min Range: -6.1381
Max Act: 5.9194. Min Act: -0.1700
Data Index: 388834 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1381. Min Range: -6.1381
Max Act: 5.8881. Min Act: -0.1700
Data Index: 2231494 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1381. Min Range: -6.1381
Max Act: 5.8881. Min Act: -0.1700
Data Index: 8569633 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1381. Min Range: -6.1381
Max Act: 5.8881. Min Act: -0.1700
Data Index: 8569636 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1381. Min Range: -6.1381
Max Act: 5.8569. Min Act: -0.1700
Data Index: 6777565 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1381. Min Range: -6.1381
Max Act: 5.8569. Min Act: -0.1700
Data Index: 3005937 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1381. Min Range: -6.1381
Max Act: 5.8569. Min Act: -0.1700
Data Index: 3005934 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1381. Min Range: -6.1381
Max Act: 5.8256. Min Act: -0.1700
Data Index: 4832131 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1381. Min Range: -6.1381
Max Act: 5.8256. Min Act: -0.1700
Data Index: 1647080 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1381. Min Range: -6.1381
Max Act: 5.8256. Min Act: -0.1700
Data Index: 4832147 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1381. Min Range: -6.1381
Max Act: 5.8256. Min Act: -0.1700
Data Index: 5625681 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1381. Min Range: -6.1381
Max Act: 5.7631. Min Act: -0.1700
Data Index: 5312934 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1381. Min Range: -6.1381
Max Act: 5.7631. Min Act: -0.1700
Data Index: 2109320 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1381. Min Range: -6.1381
Max Act: 5.7319. Min Act: -0.1700
Data Index: 4123097 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1381. Min Range: -6.1381
Max Act: 5.7631. Min Act: -0.1700
Data Index: 8078324 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19