Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2645 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.6626. Min Act: -0.1700
Data Index: 7286469 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.6626. Min Act: -0.1700
Data Index: 4368878 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.5688. Min Act: -0.1700
Data Index: 8242335 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.4438. Min Act: -0.1700
Data Index: 6453765 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.4126. Min Act: -0.1700
Data Index: 2352766 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.3501. Min Act: -0.1700
Data Index: 6623542 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.3813. Min Act: -0.1700
Data Index: 7900490 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.3501. Min Act: -0.1700
Data Index: 2431785 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.3188. Min Act: -0.1700
Data Index: 2763886 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.3188. Min Act: -0.1700
Data Index: 5142294 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.3188. Min Act: -0.1700
Data Index: 4272063 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.3188. Min Act: -0.1700
Data Index: 1692831 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.3188. Min Act: -0.1700
Data Index: 4964559 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.3188. Min Act: -0.1700
Data Index: 5690923 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.2876. Min Act: -0.1700
Data Index: 7220065 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.2876. Min Act: -0.1700
Data Index: 4960755 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.2876. Min Act: -0.1700
Data Index: 7170413 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.3188. Min Act: -0.1700
Data Index: 8584572 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.2876. Min Act: -0.1700
Data Index: 5311002 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.2563. Min Act: -0.1700
Data Index: 2398967 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19