Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1186 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.7014. Min Act: -0.1700
Data Index: 976895 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.6701. Min Act: -0.1700
Data Index: 6441506 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.6857. Min Act: -0.1700
Data Index: 8258076 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.6232. Min Act: -0.1700
Data Index: 6665888 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.6232. Min Act: -0.1700
Data Index: 7718679 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.5762. Min Act: -0.1700
Data Index: 4340803 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.6075. Min Act: -0.1700
Data Index: 6124541 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.5605. Min Act: -0.1700
Data Index: 3062143 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.5449. Min Act: -0.1700
Data Index: 5287303 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.5449. Min Act: -0.1700
Data Index: 7185684 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.5292. Min Act: -0.1700
Data Index: 1149741 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.4822. Min Act: -0.1700
Data Index: 3993531 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.4979. Min Act: -0.1700
Data Index: 1458566 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.4666. Min Act: -0.1700
Data Index: 7038670 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.4666. Min Act: -0.1700
Data Index: 3761898 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.4822. Min Act: -0.1700
Data Index: 857864 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.4822. Min Act: -0.1700
Data Index: 4611376 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.4822. Min Act: -0.1700
Data Index: 5507069 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.4979. Min Act: -0.1700
Data Index: 1697849 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7014. Min Range: -3.7014
Max Act: 3.4509. Min Act: -0.1700
Data Index: 3380738 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19