Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1108 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.7485. Min Act: -0.1700
Data Index: 710464 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.6235. Min Act: -0.1700
Data Index: 4047242 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.6235. Min Act: -0.1700
Data Index: 7566502 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.4672. Min Act: -0.1700
Data Index: 3702867 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.4360. Min Act: -0.1700
Data Index: 5504349 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.4360. Min Act: -0.1700
Data Index: 2830701 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.4360. Min Act: -0.1700
Data Index: 1883038 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.4047. Min Act: -0.1700
Data Index: 2766916 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.4360. Min Act: -0.1700
Data Index: 959348 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.3735. Min Act: -0.1700
Data Index: 1332672 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.3422. Min Act: -0.1700
Data Index: 537976 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.3110. Min Act: -0.1700
Data Index: 2721639 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.3422. Min Act: -0.1700
Data Index: 6029995 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.2797. Min Act: -0.1700
Data Index: 8446138 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.2797. Min Act: -0.1700
Data Index: 7396573 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.2797. Min Act: -0.1700
Data Index: 678516 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.3110. Min Act: -0.1700
Data Index: 1399408 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.2797. Min Act: -0.1700
Data Index: 5194380 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.2797. Min Act: -0.1700
Data Index: 7906079 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.2797. Min Act: -0.1700
Data Index: 1002895 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19