Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3859 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.0497. Min Range: -9.0497
Max Act: 9.0497. Min Act: -0.1700
Data Index: 7836010 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.9247. Min Act: -0.1700
Data Index: 2327671 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.8622. Min Act: -0.1700
Data Index: 8810475 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.8622. Min Act: -0.1700
Data Index: 5823005 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.8622. Min Act: -0.1700
Data Index: 4282657 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.7997. Min Act: -0.1700
Data Index: 5638095 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.8622. Min Act: -0.1700
Data Index: 8056633 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.7997. Min Act: -0.1700
Data Index: 6369974 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.7997. Min Act: -0.1700
Data Index: 1894650 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.8622. Min Act: -0.1700
Data Index: 2177984 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.8622. Min Act: -0.1700
Data Index: 573144 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.7997. Min Act: -0.1700
Data Index: 3095574 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.7997. Min Act: -0.1700
Data Index: 3019991 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.6747. Min Act: -0.1700
Data Index: 3433934 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.6747. Min Act: -0.1700
Data Index: 2091661 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.7372. Min Act: -0.1700
Data Index: 2199671 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.7372. Min Act: -0.1700
Data Index: 3727419 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.6747. Min Act: -0.1700
Data Index: 2985908 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.6747. Min Act: -0.1700
Data Index: 3828381 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0497. Min Range: -9.0497
Max Act: 8.6122. Min Act: -0.1700
Data Index: 1357650 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19