Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5200 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7278. Min Range: -9.7278
Max Act: 9.7278. Min Act: -0.1700
Data Index: 717204 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7278. Min Range: -9.7278
Max Act: 9.6653. Min Act: -0.1700
Data Index: 8676945 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7278. Min Range: -9.7278
Max Act: 9.2278. Min Act: -0.1700
Data Index: 7948290 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7278. Min Range: -9.7278
Max Act: 8.9778. Min Act: -0.1700
Data Index: 1718483 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7278. Min Range: -9.7278
Max Act: 8.9153. Min Act: -0.1700
Data Index: 4379527 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7278. Min Range: -9.7278
Max Act: 8.9153. Min Act: -0.1700
Data Index: 7452047 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7278. Min Range: -9.7278
Max Act: 8.8528. Min Act: -0.1700
Data Index: 897030 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7278. Min Range: -9.7278
Max Act: 8.8528. Min Act: -0.1700
Data Index: 553381 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7278. Min Range: -9.7278
Max Act: 8.7278. Min Act: -0.1700
Data Index: 7930429 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7278. Min Range: -9.7278
Max Act: 8.6653. Min Act: -0.1700
Data Index: 2928004 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7278. Min Range: -9.7278
Max Act: 8.6028. Min Act: -0.1700
Data Index: 3707691 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7278. Min Range: -9.7278
Max Act: 8.5403. Min Act: -0.1700
Data Index: 1026935 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7278. Min Range: -9.7278
Max Act: 8.5403. Min Act: -0.1700
Data Index: 5398349 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7278. Min Range: -9.7278
Max Act: 8.5403. Min Act: -0.1700
Data Index: 3238621 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7278. Min Range: -9.7278
Max Act: 8.4778. Min Act: -0.1700
Data Index: 8486657 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7278. Min Range: -9.7278
Max Act: 8.4778. Min Act: -0.1700
Data Index: 1389860 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7278. Min Range: -9.7278
Max Act: 8.4778. Min Act: -0.1700
Data Index: 5277497 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7278. Min Range: -9.7278
Max Act: 8.4153. Min Act: -0.1700
Data Index: 1809797 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7278. Min Range: -9.7278
Max Act: 8.3528. Min Act: -0.1700
Data Index: 3126006 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7278. Min Range: -9.7278
Max Act: 8.3528. Min Act: -0.1700
Data Index: 5808450 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19