Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1351. Min Range: -7.1351
Max Act: 7.1351. Min Act: -0.1700
Data Index: 7698656 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1351. Min Range: -7.1351
Max Act: 7.0726. Min Act: -0.1700
Data Index: 4150061 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1351. Min Range: -7.1351
Max Act: 6.9789. Min Act: -0.1700
Data Index: 4907810 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1351. Min Range: -7.1351
Max Act: 6.9164. Min Act: -0.1700
Data Index: 5685701 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1351. Min Range: -7.1351
Max Act: 6.8851. Min Act: -0.1700
Data Index: 8198902 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1351. Min Range: -7.1351
Max Act: 6.8226. Min Act: -0.1700
Data Index: 4579465 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1351. Min Range: -7.1351
Max Act: 6.7914. Min Act: -0.1700
Data Index: 2637951 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1351. Min Range: -7.1351
Max Act: 6.7601. Min Act: -0.1700
Data Index: 4854479 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1351. Min Range: -7.1351
Max Act: 6.6976. Min Act: -0.1700
Data Index: 6098123 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1351. Min Range: -7.1351
Max Act: 6.6976. Min Act: -0.1700
Data Index: 5342608 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1351. Min Range: -7.1351
Max Act: 6.6976. Min Act: -0.1700
Data Index: 8308530 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1351. Min Range: -7.1351
Max Act: 6.6039. Min Act: -0.1700
Data Index: 7142840 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1351. Min Range: -7.1351
Max Act: 6.5414. Min Act: -0.1700
Data Index: 5083966 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1351. Min Range: -7.1351
Max Act: 6.4476. Min Act: -0.1700
Data Index: 8025757 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1351. Min Range: -7.1351
Max Act: 6.4789. Min Act: -0.1700
Data Index: 1313376 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1351. Min Range: -7.1351
Max Act: 6.4476. Min Act: -0.1700
Data Index: 3512193 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1351. Min Range: -7.1351
Max Act: 6.4789. Min Act: -0.1700
Data Index: 7357969 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1351. Min Range: -7.1351
Max Act: 6.3851. Min Act: -0.1700
Data Index: 3466893 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1351. Min Range: -7.1351
Max Act: 6.4164. Min Act: -0.1700
Data Index: 3072491 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1351. Min Range: -7.1351
Max Act: 6.3851. Min Act: -0.1700
Data Index: 3425302 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19