Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4834 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0854. Min Range: -4.0854
Max Act: 4.0854. Min Act: -0.1700
Data Index: 8091773 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0854. Min Range: -4.0854
Max Act: 4.0229. Min Act: -0.1700
Data Index: 8091775 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0854. Min Range: -4.0854
Max Act: 3.9603. Min Act: -0.1700
Data Index: 750075 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0854. Min Range: -4.0854
Max Act: 3.9603. Min Act: -0.1700
Data Index: 3585976 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0854. Min Range: -4.0854
Max Act: 3.9291. Min Act: -0.1700
Data Index: 4811432 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0854. Min Range: -4.0854
Max Act: 3.9291. Min Act: -0.1700
Data Index: 1935773 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0854. Min Range: -4.0854
Max Act: 3.9291. Min Act: -0.1700
Data Index: 2718843 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0854. Min Range: -4.0854
Max Act: 3.8978. Min Act: -0.1700
Data Index: 531778 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0854. Min Range: -4.0854
Max Act: 3.9291. Min Act: -0.1700
Data Index: 861326 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0854. Min Range: -4.0854
Max Act: 3.8978. Min Act: -0.1700
Data Index: 113832 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0854. Min Range: -4.0854
Max Act: 3.8978. Min Act: -0.1700
Data Index: 5336254 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0854. Min Range: -4.0854
Max Act: 3.8665. Min Act: -0.1700
Data Index: 270111 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0854. Min Range: -4.0854
Max Act: 3.8665. Min Act: -0.1700
Data Index: 4350679 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0854. Min Range: -4.0854
Max Act: 3.8665. Min Act: -0.1700
Data Index: 2614665 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0854. Min Range: -4.0854
Max Act: 3.8353. Min Act: -0.1700
Data Index: 2468567 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0854. Min Range: -4.0854
Max Act: 3.8353. Min Act: -0.1700
Data Index: 4494820 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0854. Min Range: -4.0854
Max Act: 3.8353. Min Act: -0.1700
Data Index: 1059637 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0854. Min Range: -4.0854
Max Act: 3.8353. Min Act: -0.1700
Data Index: 6857405 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0854. Min Range: -4.0854
Max Act: 3.8353. Min Act: -0.1700
Data Index: 3049924 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0854. Min Range: -4.0854
Max Act: 3.8353. Min Act: -0.1700
Data Index: 346618 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19