Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1897 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.4766. Min Act: -0.1700
Data Index: 7258790 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.4414. Min Act: -0.1700
Data Index: 5545325 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.4238. Min Act: -0.1700
Data Index: 5801681 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.4238. Min Act: -0.1698
Data Index: 4454987 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.4238. Min Act: -0.1700
Data Index: 1034523 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.4062. Min Act: -0.1700
Data Index: 1474197 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.3886. Min Act: -0.1700
Data Index: 7252683 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.3886. Min Act: -0.1700
Data Index: 2672092 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.4062. Min Act: -0.1700
Data Index: 4052672 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.3886. Min Act: -0.1700
Data Index: 5616037 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.3886. Min Act: -0.1700
Data Index: 8777403 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.3886. Min Act: -0.1699
Data Index: 8694470 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.3710. Min Act: -0.1700
Data Index: 1231888 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.3710. Min Act: -0.1700
Data Index: 5796699 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.3886. Min Act: -0.1700
Data Index: 1721931 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.3710. Min Act: -0.1700
Data Index: 3597977 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.3710. Min Act: -0.1700
Data Index: 3933755 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.3710. Min Act: -0.1700
Data Index: 537092 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.3533. Min Act: -0.1700
Data Index: 6254572 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4766. Min Range: -1.4766
Max Act: 1.3533. Min Act: -0.1700
Data Index: 6797455 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19