Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 938 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.7035. Min Act: -0.1700
Data Index: 5266275 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.6723. Min Act: -0.1700
Data Index: 4315680 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.5160. Min Act: -0.1700
Data Index: 3765523 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.4223. Min Act: -0.1700
Data Index: 3587470 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.4535. Min Act: -0.1700
Data Index: 7329569 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.4223. Min Act: -0.1700
Data Index: 2464583 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.4223. Min Act: -0.1700
Data Index: 246832 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.3910. Min Act: -0.1700
Data Index: 5631816 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.3910. Min Act: -0.1700
Data Index: 1101551 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.3910. Min Act: -0.1700
Data Index: 554520 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.3910. Min Act: -0.1700
Data Index: 6376581 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.3598. Min Act: -0.1700
Data Index: 4085693 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.3598. Min Act: -0.1700
Data Index: 261121 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.3285. Min Act: -0.1700
Data Index: 300786 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.3285. Min Act: -0.1700
Data Index: 1184771 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.3285. Min Act: -0.1700
Data Index: 49331 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.3285. Min Act: -0.1700
Data Index: 2462782 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.2972. Min Act: -0.1700
Data Index: 1420455 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.2660. Min Act: -0.1700
Data Index: 1421441 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7035. Min Range: -4.7035
Max Act: 4.2347. Min Act: -0.1700
Data Index: 3067447 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19