Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1869 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.6528. Min Act: -0.1700
Data Index: 1414700 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.5591. Min Act: -0.1700
Data Index: 4926904 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.4966. Min Act: -0.1700
Data Index: 4766545 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.4341. Min Act: -0.1700
Data Index: 6293692 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.3716. Min Act: -0.1700
Data Index: 5252664 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.3716. Min Act: -0.1700
Data Index: 8333445 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.2466. Min Act: -0.1700
Data Index: 2835886 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.2466. Min Act: -0.1700
Data Index: 7912891 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.2466. Min Act: -0.1700
Data Index: 6751134 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.1841. Min Act: -0.1700
Data Index: 2594101 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.1841. Min Act: -0.1700
Data Index: 4941247 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.2153. Min Act: -0.1700
Data Index: 5947222 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.1528. Min Act: -0.1700
Data Index: 77218 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.1841. Min Act: -0.1700
Data Index: 1168303 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.1528. Min Act: -0.1700
Data Index: 7575815 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.1216. Min Act: -0.1700
Data Index: 2578639 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.1216. Min Act: -0.1700
Data Index: 832512 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.1216. Min Act: -0.1700
Data Index: 8784585 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.1216. Min Act: -0.1700
Data Index: 5134720 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6528. Min Range: -5.6528
Max Act: 5.0903. Min Act: -0.1700
Data Index: 3381470 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19