Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1012 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.9130. Min Act: -0.1700
Data Index: 3196145 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.8818. Min Act: -0.1700
Data Index: 8010329 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.7880. Min Act: -0.1700
Data Index: 2975170 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.8192. Min Act: -0.1700
Data Index: 2676739 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.8192. Min Act: -0.1700
Data Index: 738470 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.8505. Min Act: -0.1700
Data Index: 3464623 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.7880. Min Act: -0.1700
Data Index: 4508088 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.7880. Min Act: -0.1700
Data Index: 4679420 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.8192. Min Act: -0.1700
Data Index: 1754435 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.8192. Min Act: -0.1700
Data Index: 3942237 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.7880. Min Act: -0.1700
Data Index: 4508247 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.7880. Min Act: -0.1700
Data Index: 6865036 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.7880. Min Act: -0.1700
Data Index: 5715777 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.7880. Min Act: -0.1700
Data Index: 2409200 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.8192. Min Act: -0.1700
Data Index: 4515160 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.8192. Min Act: -0.1700
Data Index: 2376130 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.7880. Min Act: -0.1700
Data Index: 3284941 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.7880. Min Act: -0.1700
Data Index: 3280256 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.7880. Min Act: -0.1700
Data Index: 2648634 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9130. Min Range: -3.9130
Max Act: 3.7880. Min Act: -0.1700
Data Index: 1643475 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19