Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 829 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6018. Min Range: -9.6018
Max Act: 9.6018. Min Act: -0.1700
Data Index: 1824824 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6018. Min Range: -9.6018
Max Act: 9.2893. Min Act: -0.1700
Data Index: 3885414 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6018. Min Range: -9.6018
Max Act: 9.2893. Min Act: -0.1700
Data Index: 419168 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6018. Min Range: -9.6018
Max Act: 9.2268. Min Act: -0.1700
Data Index: 2701551 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6018. Min Range: -9.6018
Max Act: 9.1018. Min Act: -0.1700
Data Index: 8218180 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6018. Min Range: -9.6018
Max Act: 9.1018. Min Act: -0.1700
Data Index: 1104086 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6018. Min Range: -9.6018
Max Act: 9.1018. Min Act: -0.1700
Data Index: 2162535 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6018. Min Range: -9.6018
Max Act: 9.0393. Min Act: -0.1700
Data Index: 1043946 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6018. Min Range: -9.6018
Max Act: 8.9143. Min Act: -0.1700
Data Index: 109563 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6018. Min Range: -9.6018
Max Act: 8.8518. Min Act: -0.1700
Data Index: 1068219 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6018. Min Range: -9.6018
Max Act: 8.7893. Min Act: -0.1700
Data Index: 1369652 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6018. Min Range: -9.6018
Max Act: 8.7893. Min Act: -0.1700
Data Index: 5729942 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6018. Min Range: -9.6018
Max Act: 8.7893. Min Act: -0.1700
Data Index: 3345582 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6018. Min Range: -9.6018
Max Act: 8.7893. Min Act: -0.1700
Data Index: 6452477 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6018. Min Range: -9.6018
Max Act: 8.8518. Min Act: -0.1700
Data Index: 4947180 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6018. Min Range: -9.6018
Max Act: 8.7268. Min Act: -0.1700
Data Index: 3753177 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6018. Min Range: -9.6018
Max Act: 8.7268. Min Act: -0.1700
Data Index: 1595934 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6018. Min Range: -9.6018
Max Act: 8.6643. Min Act: -0.1700
Data Index: 2023259 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6018. Min Range: -9.6018
Max Act: 8.6643. Min Act: -0.1700
Data Index: 4056186 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6018. Min Range: -9.6018
Max Act: 8.6643. Min Act: -0.1700
Data Index: 6473110 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19