Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3436 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0128. Min Range: -5.0128
Max Act: 5.0128. Min Act: -0.1700
Data Index: 3258049 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.9816. Min Act: -0.1700
Data Index: 8296618 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.9191. Min Act: -0.1700
Data Index: 8784457 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8878. Min Act: -0.1700
Data Index: 8296617 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8566. Min Act: -0.1700
Data Index: 5156968 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8253. Min Act: -0.1700
Data Index: 4842763 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8566. Min Act: -0.1700
Data Index: 6475121 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8566. Min Act: -0.1700
Data Index: 7202713 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8878. Min Act: -0.1700
Data Index: 1840645 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8566. Min Act: -0.1700
Data Index: 1967979 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8253. Min Act: -0.1700
Data Index: 2172611 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8253. Min Act: -0.1700
Data Index: 8806030 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8253. Min Act: -0.1700
Data Index: 3884571 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8253. Min Act: -0.1700
Data Index: 3799025 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8253. Min Act: -0.1700
Data Index: 7699544 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8253. Min Act: -0.1700
Data Index: 3333906 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8253. Min Act: -0.1700
Data Index: 7391668 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8253. Min Act: -0.1700
Data Index: 1726271 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8253. Min Act: -0.1700
Data Index: 6151841 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.7941. Min Act: -0.1700
Data Index: 2167471 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19