Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1590 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.2950. Min Range: -9.2950
Max Act: 9.2325. Min Act: -0.1700
Data Index: 4661689 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2950. Min Range: -9.2950
Max Act: 9.2950. Min Act: -0.1700
Data Index: 812518 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2950. Min Range: -9.2950
Max Act: 8.9825. Min Act: -0.1700
Data Index: 325794 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2950. Min Range: -9.2950
Max Act: 8.9825. Min Act: -0.1700
Data Index: 6220586 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2950. Min Range: -9.2950
Max Act: 9.0450. Min Act: -0.1700
Data Index: 495830 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2950. Min Range: -9.2950
Max Act: 8.9200. Min Act: -0.1700
Data Index: 8641308 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2950. Min Range: -9.2950
Max Act: 8.9200. Min Act: -0.1700
Data Index: 8360607 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2950. Min Range: -9.2950
Max Act: 8.8575. Min Act: -0.1700
Data Index: 8704481 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2950. Min Range: -9.2950
Max Act: 8.7950. Min Act: -0.1700
Data Index: 1333303 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2950. Min Range: -9.2950
Max Act: 8.7325. Min Act: -0.1700
Data Index: 8152209 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2950. Min Range: -9.2950
Max Act: 8.6700. Min Act: -0.1700
Data Index: 6289599 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2950. Min Range: -9.2950
Max Act: 8.6700. Min Act: -0.1700
Data Index: 7183160 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2950. Min Range: -9.2950
Max Act: 8.7325. Min Act: -0.1700
Data Index: 7629844 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2950. Min Range: -9.2950
Max Act: 8.7325. Min Act: -0.1700
Data Index: 426776 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2950. Min Range: -9.2950
Max Act: 8.6700. Min Act: -0.1700
Data Index: 938443 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2950. Min Range: -9.2950
Max Act: 8.6075. Min Act: -0.1700
Data Index: 4051259 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2950. Min Range: -9.2950
Max Act: 8.6075. Min Act: -0.1700
Data Index: 7434034 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2950. Min Range: -9.2950
Max Act: 8.6075. Min Act: -0.1700
Data Index: 8078850 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2950. Min Range: -9.2950
Max Act: 8.6075. Min Act: -0.1700
Data Index: 3578131 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2950. Min Range: -9.2950
Max Act: 8.6700. Min Act: -0.1700
Data Index: 3401922 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19