Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3841 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9174. Min Range: -6.9174
Max Act: 6.9174. Min Act: -0.1700
Data Index: 8583653 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9174. Min Range: -6.9174
Max Act: 6.3862. Min Act: -0.1700
Data Index: 2174981 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9174. Min Range: -6.9174
Max Act: 5.5424. Min Act: -0.1699
Data Index: 5175041 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9174. Min Range: -6.9174
Max Act: 5.7612. Min Act: -0.1699
Data Index: 1280223 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9174. Min Range: -6.9174
Max Act: 5.9174. Min Act: -0.1700
Data Index: 966303 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9174. Min Range: -6.9174
Max Act: 5.8862. Min Act: -0.1668
Data Index: 288829 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9174. Min Range: -6.9174
Max Act: 5.7299. Min Act: -0.1700
Data Index: 5032178 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9174. Min Range: -6.9174
Max Act: 5.5737. Min Act: -0.1700
Data Index: 3522601 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9174. Min Range: -6.9174
Max Act: 4.8237. Min Act: -0.1700
Data Index: 8797144 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9174. Min Range: -6.9174
Max Act: 5.5737. Min Act: -0.1686
Data Index: 3206635 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9174. Min Range: -6.9174
Max Act: 5.7612. Min Act: -0.1693
Data Index: 288827 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9174. Min Range: -6.9174
Max Act: 5.7612. Min Act: -0.1700
Data Index: 4902399 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9174. Min Range: -6.9174
Max Act: 5.5737. Min Act: -0.1699
Data Index: 1878621 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9174. Min Range: -6.9174
Max Act: 5.5112. Min Act: -0.1700
Data Index: 3232610 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9174. Min Range: -6.9174
Max Act: 5.5737. Min Act: -0.1695
Data Index: 6379865 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9174. Min Range: -6.9174
Max Act: 5.6362. Min Act: -0.1700
Data Index: 5262993 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9174. Min Range: -6.9174
Max Act: 6.6362. Min Act: -0.1699
Data Index: 2127993 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9174. Min Range: -6.9174
Max Act: 5.3862. Min Act: -0.1698
Data Index: 5503997 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9174. Min Range: -6.9174
Max Act: 5.5737. Min Act: -0.1699
Data Index: 6790678 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9174. Min Range: -6.9174
Max Act: 5.6362. Min Act: -0.1700
Data Index: 5645527 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19