Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5138 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0656. Min Range: -10.0656
Max Act: 10.0656. Min Act: -0.1700
Data Index: 806731 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0656. Min Range: -10.0656
Max Act: 9.5031. Min Act: -0.1700
Data Index: 6264593 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0656. Min Range: -10.0656
Max Act: 9.4406. Min Act: -0.1700
Data Index: 4631177 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0656. Min Range: -10.0656
Max Act: 9.1906. Min Act: -0.1700
Data Index: 2228564 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0656. Min Range: -10.0656
Max Act: 9.2531. Min Act: -0.1700
Data Index: 359408 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0656. Min Range: -10.0656
Max Act: 9.1906. Min Act: -0.1700
Data Index: 3343789 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0656. Min Range: -10.0656
Max Act: 9.1281. Min Act: -0.1700
Data Index: 8712379 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0656. Min Range: -10.0656
Max Act: 9.0031. Min Act: -0.1700
Data Index: 4322565 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0656. Min Range: -10.0656
Max Act: 9.0656. Min Act: -0.1700
Data Index: 6478755 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0656. Min Range: -10.0656
Max Act: 9.0031. Min Act: -0.1700
Data Index: 194253 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0656. Min Range: -10.0656
Max Act: 9.0031. Min Act: -0.1700
Data Index: 4437557 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0656. Min Range: -10.0656
Max Act: 8.9406. Min Act: -0.1700
Data Index: 52873 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0656. Min Range: -10.0656
Max Act: 9.0031. Min Act: -0.1700
Data Index: 4919642 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0656. Min Range: -10.0656
Max Act: 9.0656. Min Act: -0.1700
Data Index: 1181454 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0656. Min Range: -10.0656
Max Act: 8.9406. Min Act: -0.1700
Data Index: 6602377 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0656. Min Range: -10.0656
Max Act: 8.9406. Min Act: -0.1700
Data Index: 4648427 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0656. Min Range: -10.0656
Max Act: 8.9406. Min Act: -0.1700
Data Index: 8050377 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0656. Min Range: -10.0656
Max Act: 8.9406. Min Act: -0.1700
Data Index: 6477573 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0656. Min Range: -10.0656
Max Act: 8.9406. Min Act: -0.1700
Data Index: 5522376 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0656. Min Range: -10.0656
Max Act: 8.9406. Min Act: -0.1700
Data Index: 3379060 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19