Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 42 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.9106. Min Act: -0.1700
Data Index: 4684699 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.5981. Min Act: -0.1700
Data Index: 8515191 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.5356. Min Act: -0.1700
Data Index: 957165 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.3481. Min Act: -0.1700
Data Index: 8795813 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.2856. Min Act: -0.1700
Data Index: 1641274 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.2856. Min Act: -0.1700
Data Index: 1391642 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.2856. Min Act: -0.1700
Data Index: 8407476 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.2231. Min Act: -0.1700
Data Index: 8776947 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.1606. Min Act: -0.1700
Data Index: 1192383 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.2231. Min Act: -0.1700
Data Index: 2406748 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.2231. Min Act: -0.1700
Data Index: 5183339 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.2231. Min Act: -0.1700
Data Index: 4306540 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.1606. Min Act: -0.1700
Data Index: 2104017 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.1606. Min Act: -0.1700
Data Index: 6139647 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.1606. Min Act: -0.1700
Data Index: 4330512 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.2231. Min Act: -0.1700
Data Index: 7969015 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.1606. Min Act: -0.1700
Data Index: 409696 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.1606. Min Act: -0.1700
Data Index: 4263491 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.1606. Min Act: -0.1700
Data Index: 3757099 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9106. Min Range: -9.9106
Max Act: 9.0981. Min Act: -0.1700
Data Index: 2240044 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19