Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.3704. Min Act: -0.1700
Data Index: 5554959 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 1838438 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 3477684 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 2356828 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 278122 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 293392 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 3248537 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 2363351 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 2918220 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 314346 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 232543 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 438554 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 64578 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 855591 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 2731028 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 1533952 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 353838 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 1422937 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 402951 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3704. Min Range: -2.3704
Max Act: 2.0890. Min Act: -0.1700
Data Index: 974701 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19