Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3279 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2527. Min Range: -8.2527
Max Act: 8.2527. Min Act: -0.1700
Data Index: 2184104 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2527. Min Range: -8.2527
Max Act: 8.1902. Min Act: -0.1700
Data Index: 8016471 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2527. Min Range: -8.2527
Max Act: 7.9402. Min Act: -0.1700
Data Index: 1822723 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2527. Min Range: -8.2527
Max Act: 7.8777. Min Act: -0.1700
Data Index: 4882426 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2527. Min Range: -8.2527
Max Act: 7.8152. Min Act: -0.1700
Data Index: 1003423 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2527. Min Range: -8.2527
Max Act: 7.7840. Min Act: -0.1700
Data Index: 3964284 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2527. Min Range: -8.2527
Max Act: 7.6590. Min Act: -0.1700
Data Index: 1651902 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2527. Min Range: -8.2527
Max Act: 7.6277. Min Act: -0.1700
Data Index: 4288959 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2527. Min Range: -8.2527
Max Act: 7.6277. Min Act: -0.1700
Data Index: 4558649 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2527. Min Range: -8.2527
Max Act: 7.5965. Min Act: -0.1700
Data Index: 6115744 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2527. Min Range: -8.2527
Max Act: 7.6277. Min Act: -0.1700
Data Index: 6812912 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2527. Min Range: -8.2527
Max Act: 7.5652. Min Act: -0.1700
Data Index: 7565266 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2527. Min Range: -8.2527
Max Act: 7.5340. Min Act: -0.1700
Data Index: 8030982 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2527. Min Range: -8.2527
Max Act: 7.5340. Min Act: -0.1700
Data Index: 7453754 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2527. Min Range: -8.2527
Max Act: 7.4715. Min Act: -0.1700
Data Index: 7007621 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2527. Min Range: -8.2527
Max Act: 7.4715. Min Act: -0.1700
Data Index: 338416 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2527. Min Range: -8.2527
Max Act: 7.4402. Min Act: -0.1700
Data Index: 751256 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2527. Min Range: -8.2527
Max Act: 7.4402. Min Act: -0.1700
Data Index: 411364 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2527. Min Range: -8.2527
Max Act: 7.4090. Min Act: -0.1700
Data Index: 4616242 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2527. Min Range: -8.2527
Max Act: 7.4090. Min Act: -0.1700
Data Index: 4466201 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19