Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3051 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.8109. Min Act: -0.1700
Data Index: 8809025 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.7172. Min Act: -0.1700
Data Index: 6177971 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.7484. Min Act: -0.1700
Data Index: 596333 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.6234. Min Act: -0.1700
Data Index: 11372 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.4672. Min Act: -0.1700
Data Index: 7121435 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.4984. Min Act: -0.1700
Data Index: 2678112 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.4359. Min Act: -0.1700
Data Index: 6140254 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.4359. Min Act: -0.1700
Data Index: 3015831 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.4359. Min Act: -0.1700
Data Index: 3924609 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.4672. Min Act: -0.1700
Data Index: 5516850 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.3734. Min Act: -0.1700
Data Index: 1646749 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.4047. Min Act: -0.1700
Data Index: 5793336 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.4047. Min Act: -0.1700
Data Index: 1531234 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.3734. Min Act: -0.1700
Data Index: 2670968 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.3734. Min Act: -0.1700
Data Index: 5058097 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.3734. Min Act: -0.1700
Data Index: 172096 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.3422. Min Act: -0.1700
Data Index: 72019 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.3422. Min Act: -0.1700
Data Index: 5012508 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.3422. Min Act: -0.1700
Data Index: 1190304 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8109. Min Range: -4.8109
Max Act: 4.3422. Min Act: -0.1700
Data Index: 2954090 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19