Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3550 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.4512. Min Act: -0.1700
Data Index: 7573684 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.4512. Min Act: -0.1700
Data Index: 1384431 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.3575. Min Act: -0.1700
Data Index: 6254755 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.3575. Min Act: -0.1700
Data Index: 2846754 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.3575. Min Act: -0.1700
Data Index: 3193336 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.2325. Min Act: -0.1700
Data Index: 6998192 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.2637. Min Act: -0.1700
Data Index: 1384434 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.2637. Min Act: -0.1700
Data Index: 2712613 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.2325. Min Act: -0.1700
Data Index: 572026 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.2325. Min Act: -0.1700
Data Index: 7109397 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.2325. Min Act: -0.1700
Data Index: 6288866 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.2012. Min Act: -0.1700
Data Index: 7528458 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.1700. Min Act: -0.1700
Data Index: 2536330 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.1700. Min Act: -0.1700
Data Index: 632103 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.1700. Min Act: -0.1700
Data Index: 8646358 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.1387. Min Act: -0.1700
Data Index: 1866289 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.1387. Min Act: -0.1700
Data Index: 2498056 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.1387. Min Act: -0.1700
Data Index: 3063347 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.1700. Min Act: -0.1700
Data Index: 749328 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4512. Min Range: -4.4512
Max Act: 4.1387. Min Act: -0.1700
Data Index: 7436453 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19