Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4835 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2545. Min Range: -5.2545
Max Act: 5.2545. Min Act: -0.1700
Data Index: 4959922 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2545. Min Range: -5.2545
Max Act: 5.1295. Min Act: -0.1700
Data Index: 6530708 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2545. Min Range: -5.2545
Max Act: 5.1295. Min Act: -0.1700
Data Index: 7015313 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2545. Min Range: -5.2545
Max Act: 5.1608. Min Act: -0.1700
Data Index: 3936456 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2545. Min Range: -5.2545
Max Act: 5.0983. Min Act: -0.1700
Data Index: 1449319 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2545. Min Range: -5.2545
Max Act: 5.0983. Min Act: -0.1700
Data Index: 7689980 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2545. Min Range: -5.2545
Max Act: 5.0983. Min Act: -0.1700
Data Index: 4222808 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2545. Min Range: -5.2545
Max Act: 5.0358. Min Act: -0.1700
Data Index: 4342838 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2545. Min Range: -5.2545
Max Act: 5.0358. Min Act: -0.1700
Data Index: 4632586 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2545. Min Range: -5.2545
Max Act: 5.0358. Min Act: -0.1700
Data Index: 675114 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2545. Min Range: -5.2545
Max Act: 5.0358. Min Act: -0.1700
Data Index: 1688747 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2545. Min Range: -5.2545
Max Act: 5.0045. Min Act: -0.1700
Data Index: 553376 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2545. Min Range: -5.2545
Max Act: 5.0358. Min Act: -0.1700
Data Index: 1831558 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2545. Min Range: -5.2545
Max Act: 5.0045. Min Act: -0.1700
Data Index: 8266742 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2545. Min Range: -5.2545
Max Act: 5.0045. Min Act: -0.1700
Data Index: 1274593 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2545. Min Range: -5.2545
Max Act: 5.0045. Min Act: -0.1700
Data Index: 1258574 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2545. Min Range: -5.2545
Max Act: 4.9733. Min Act: -0.1700
Data Index: 3966332 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2545. Min Range: -5.2545
Max Act: 4.9733. Min Act: -0.1700
Data Index: 3297981 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2545. Min Range: -5.2545
Max Act: 4.9733. Min Act: -0.1700
Data Index: 3227129 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2545. Min Range: -5.2545
Max Act: 4.9733. Min Act: -0.1700
Data Index: 2589662 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19