Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 924 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3007. Min Range: -4.3007
Max Act: 4.3007. Min Act: -0.1700
Data Index: 1175431 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3007. Min Range: -4.3007
Max Act: 4.2694. Min Act: -0.1700
Data Index: 1175434 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3007. Min Range: -4.3007
Max Act: 4.2069. Min Act: -0.1700
Data Index: 7049921 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3007. Min Range: -4.3007
Max Act: 4.1757. Min Act: -0.1700
Data Index: 4954587 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3007. Min Range: -4.3007
Max Act: 4.1444. Min Act: -0.1700
Data Index: 7049912 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3007. Min Range: -4.3007
Max Act: 4.1131. Min Act: -0.1700
Data Index: 6570135 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3007. Min Range: -4.3007
Max Act: 4.1131. Min Act: -0.1700
Data Index: 1338311 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3007. Min Range: -4.3007
Max Act: 4.0819. Min Act: -0.1700
Data Index: 1632737 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3007. Min Range: -4.3007
Max Act: 4.0819. Min Act: -0.1700
Data Index: 6267770 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3007. Min Range: -4.3007
Max Act: 4.0506. Min Act: -0.1700
Data Index: 6843390 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3007. Min Range: -4.3007
Max Act: 4.0506. Min Act: -0.1700
Data Index: 1175432 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3007. Min Range: -4.3007
Max Act: 4.0506. Min Act: -0.1700
Data Index: 1175433 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3007. Min Range: -4.3007
Max Act: 4.0506. Min Act: -0.1700
Data Index: 6267771 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3007. Min Range: -4.3007
Max Act: 4.0506. Min Act: -0.1700
Data Index: 7049907 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3007. Min Range: -4.3007
Max Act: 3.9881. Min Act: -0.1700
Data Index: 7049919 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3007. Min Range: -4.3007
Max Act: 3.9881. Min Act: -0.1700
Data Index: 6267769 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3007. Min Range: -4.3007
Max Act: 3.9568. Min Act: -0.1700
Data Index: 7049901 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3007. Min Range: -4.3007
Max Act: 3.9881. Min Act: -0.1700
Data Index: 7049915 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3007. Min Range: -4.3007
Max Act: 3.9881. Min Act: -0.1700
Data Index: 6570133 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3007. Min Range: -4.3007
Max Act: 3.9568. Min Act: -0.1700
Data Index: 6570134 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19