Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.8797. Min Act: -0.1700
Data Index: 8143214 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.7234. Min Act: -0.1700
Data Index: 1114800 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.6922. Min Act: -0.1700
Data Index: 5885682 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.5359. Min Act: -0.1700
Data Index: 2199057 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.5359. Min Act: -0.1700
Data Index: 6319205 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.5047. Min Act: -0.1700
Data Index: 1570212 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.4734. Min Act: -0.1700
Data Index: 4427534 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.5359. Min Act: -0.1700
Data Index: 4827767 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.5359. Min Act: -0.1700
Data Index: 3423797 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.4422. Min Act: -0.1700
Data Index: 391949 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.4734. Min Act: -0.1700
Data Index: 7519722 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.4109. Min Act: -0.1700
Data Index: 690398 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.4109. Min Act: -0.1700
Data Index: 3321895 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.4422. Min Act: -0.1700
Data Index: 3550359 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.4109. Min Act: -0.1700
Data Index: 1838876 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.3797. Min Act: -0.1700
Data Index: 6022676 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.3484. Min Act: -0.1700
Data Index: 7759646 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.3484. Min Act: -0.1700
Data Index: 6450889 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.3172. Min Act: -0.1700
Data Index: 6193277 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8797. Min Range: -5.8797
Max Act: 5.3172. Min Act: -0.1700
Data Index: 4820198 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19