Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1960 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.4935. Min Act: -0.1700
Data Index: 743807 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.4143. Min Act: -0.1700
Data Index: 5147045 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.3967. Min Act: -0.1700
Data Index: 1812317 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.3702. Min Act: -0.1700
Data Index: 7252576 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.3791. Min Act: -0.1695
Data Index: 4613867 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.3702. Min Act: -0.1700
Data Index: 4581879 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.3526. Min Act: -0.1700
Data Index: 5543784 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.3614. Min Act: -0.1700
Data Index: 2523105 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.3614. Min Act: -0.1700
Data Index: 5886568 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.3526. Min Act: -0.1700
Data Index: 735809 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.3438. Min Act: -0.1700
Data Index: 5521119 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.3526. Min Act: -0.1696
Data Index: 722101 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.3350. Min Act: -0.1700
Data Index: 3056045 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.3438. Min Act: -0.1700
Data Index: 6654036 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.3350. Min Act: -0.1700
Data Index: 8042261 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.3350. Min Act: -0.1700
Data Index: 7849011 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.3350. Min Act: -0.1700
Data Index: 4262952 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.3262. Min Act: -0.1700
Data Index: 8578140 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.3262. Min Act: -0.1700
Data Index: 8670686 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4935. Min Range: -1.4935
Max Act: 1.3350. Min Act: -0.1700
Data Index: 1979997 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19