Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1147 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3612. Min Act: -0.1700
Data Index: 2160465 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3775. Min Act: -0.1700
Data Index: 7794170 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3612. Min Act: -0.1700
Data Index: 1469401 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3448. Min Act: -0.1700
Data Index: 5006027 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3612. Min Act: -0.1700
Data Index: 2099997 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3612. Min Act: -0.1700
Data Index: 2833727 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3612. Min Act: -0.1700
Data Index: 6826933 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3120. Min Act: -0.1700
Data Index: 4673003 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3120. Min Act: -0.1700
Data Index: 8140301 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3448. Min Act: -0.1700
Data Index: 5560979 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3448. Min Act: -0.1700
Data Index: 3440684 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3284. Min Act: -0.1700
Data Index: 657700 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3284. Min Act: -0.1700
Data Index: 7268255 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3284. Min Act: -0.1700
Data Index: 5547353 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3120. Min Act: -0.1700
Data Index: 537193 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3284. Min Act: -0.1700
Data Index: 6826621 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3120. Min Act: -0.1700
Data Index: 5339462 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3284. Min Act: -0.1700
Data Index: 5006437 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.3284. Min Act: -0.1700
Data Index: 6271644 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3775. Min Range: -2.3775
Max Act: 2.2955. Min Act: -0.1700
Data Index: 3664176 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19