Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3384 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2002. Min Range: -8.2002
Max Act: 8.2002. Min Act: -0.1700
Data Index: 5212777 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.9502. Min Act: -0.1700
Data Index: 7523089 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.8877. Min Act: -0.1700
Data Index: 2800668 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.7002. Min Act: -0.1700
Data Index: 1609449 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.7002. Min Act: -0.1700
Data Index: 6377075 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.7002. Min Act: -0.1700
Data Index: 566866 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.6377. Min Act: -0.1699
Data Index: 5282224 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.5440. Min Act: -0.1700
Data Index: 8240395 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.5440. Min Act: -0.1700
Data Index: 682804 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.5127. Min Act: -0.1700
Data Index: 1655921 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.4190. Min Act: -0.1700
Data Index: 4567679 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.4502. Min Act: -0.1700
Data Index: 620190 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.4190. Min Act: -0.1700
Data Index: 4656916 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.4190. Min Act: -0.1700
Data Index: 6874866 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.3565. Min Act: -0.1700
Data Index: 7122953 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.3877. Min Act: -0.1700
Data Index: 3662976 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.3877. Min Act: -0.1700
Data Index: 4277076 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.3252. Min Act: -0.1700
Data Index: 4888491 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.3877. Min Act: -0.1700
Data Index: 5963542 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2002. Min Range: -8.2002
Max Act: 7.3877. Min Act: -0.1700
Data Index: 292688 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19