Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 394 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.1634. Min Range: -10.1634
Max Act: 10.1634. Min Act: -0.1699
Data Index: 4839793 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.9134. Min Act: -0.1699
Data Index: 314924 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.8509. Min Act: -0.1700
Data Index: 634948 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.5384. Min Act: -0.1700
Data Index: 2843046 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.4759. Min Act: -0.1700
Data Index: 3818038 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.4759. Min Act: -0.1699
Data Index: 7611925 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.4759. Min Act: -0.1700
Data Index: 5154105 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.4759. Min Act: -0.1700
Data Index: 629486 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.4759. Min Act: -0.1700
Data Index: 6700207 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.4134. Min Act: -0.1700
Data Index: 807864 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.4134. Min Act: -0.1700
Data Index: 4281537 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.4134. Min Act: -0.1700
Data Index: 1221998 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.2884. Min Act: -0.1700
Data Index: 1699802 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.2884. Min Act: -0.1700
Data Index: 5187208 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.2259. Min Act: -0.1700
Data Index: 2618084 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.1009. Min Act: -0.1700
Data Index: 4448165 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.1634. Min Act: -0.1700
Data Index: 408691 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.2259. Min Act: -0.1700
Data Index: 5015384 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.2259. Min Act: -0.1700
Data Index: 6251144 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1634. Min Range: -10.1634
Max Act: 9.2259. Min Act: -0.1700
Data Index: 6098539 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19