Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4064 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5822. Min Range: -7.5822
Max Act: 7.5822. Min Act: -0.1700
Data Index: 1218557 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5822. Min Range: -7.5822
Max Act: 7.3947. Min Act: -0.1700
Data Index: 303036 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5822. Min Range: -7.5822
Max Act: 7.3635. Min Act: -0.1700
Data Index: 2014761 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5822. Min Range: -7.5822
Max Act: 7.3322. Min Act: -0.1700
Data Index: 1254490 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5822. Min Range: -7.5822
Max Act: 7.3322. Min Act: -0.1700
Data Index: 4891779 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5822. Min Range: -7.5822
Max Act: 7.2385. Min Act: -0.1700
Data Index: 1161826 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5822. Min Range: -7.5822
Max Act: 7.2697. Min Act: -0.1700
Data Index: 4410254 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5822. Min Range: -7.5822
Max Act: 7.3010. Min Act: -0.1700
Data Index: 2404873 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5822. Min Range: -7.5822
Max Act: 7.1760. Min Act: -0.1700
Data Index: 2904939 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5822. Min Range: -7.5822
Max Act: 7.2697. Min Act: -0.1700
Data Index: 6460076 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5822. Min Range: -7.5822
Max Act: 7.0197. Min Act: -0.1700
Data Index: 3002575 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5822. Min Range: -7.5822
Max Act: 7.0822. Min Act: -0.1700
Data Index: 3414641 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5822. Min Range: -7.5822
Max Act: 7.0197. Min Act: -0.1700
Data Index: 8370608 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5822. Min Range: -7.5822
Max Act: 6.9885. Min Act: -0.1700
Data Index: 2749746 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5822. Min Range: -7.5822
Max Act: 6.9885. Min Act: -0.1700
Data Index: 1713386 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5822. Min Range: -7.5822
Max Act: 6.6760. Min Act: -0.1700
Data Index: 4412937 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5822. Min Range: -7.5822
Max Act: 6.9572. Min Act: -0.1700
Data Index: 3581765 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5822. Min Range: -7.5822
Max Act: 6.9885. Min Act: -0.1700
Data Index: 521673 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5822. Min Range: -7.5822
Max Act: 6.9260. Min Act: -0.1700
Data Index: 4246958 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5822. Min Range: -7.5822
Max Act: 6.9260. Min Act: -0.1700
Data Index: 8365773 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19