Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 913 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.7802. Min Act: -0.1700
Data Index: 1458934 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.6240. Min Act: -0.1700
Data Index: 2991546 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.4677. Min Act: -0.1700
Data Index: 3309903 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.4365. Min Act: -0.1700
Data Index: 5282218 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.4365. Min Act: -0.1700
Data Index: 8186516 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.4365. Min Act: -0.1700
Data Index: 3574527 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.4052. Min Act: -0.1700
Data Index: 2842826 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.4052. Min Act: -0.1700
Data Index: 7498960 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.3740. Min Act: -0.1700
Data Index: 6447764 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.3427. Min Act: -0.1700
Data Index: 6902323 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.3115. Min Act: -0.1700
Data Index: 5308933 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.3115. Min Act: -0.1700
Data Index: 4499106 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.3115. Min Act: -0.1700
Data Index: 1038121 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.2802. Min Act: -0.1700
Data Index: 7769594 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.2802. Min Act: -0.1700
Data Index: 6717712 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.2490. Min Act: -0.1700
Data Index: 4229050 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.2490. Min Act: -0.1700
Data Index: 7510458 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.3115. Min Act: -0.1700
Data Index: 6654006 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.2490. Min Act: -0.1700
Data Index: 4877610 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7802. Min Range: -6.7802
Max Act: 6.2177. Min Act: -0.1700
Data Index: 5473714 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19