Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 41 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0136. Min Range: -2.0136
Max Act: 2.0136. Min Act: -0.1699
Data Index: 5950877 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9967. Min Act: -0.1700
Data Index: 5785201 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9798. Min Act: -0.1700
Data Index: 5950876 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9798. Min Act: -0.1700
Data Index: 768865 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9713. Min Act: -0.1700
Data Index: 7566552 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9544. Min Act: -0.1699
Data Index: 2672687 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9544. Min Act: -0.1700
Data Index: 3144758 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9374. Min Act: -0.1699
Data Index: 3747966 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9459. Min Act: -0.1700
Data Index: 2899731 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9459. Min Act: -0.1700
Data Index: 6273719 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9459. Min Act: -0.1700
Data Index: 3902548 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9289. Min Act: -0.1700
Data Index: 4508094 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9289. Min Act: -0.1699
Data Index: 4526420 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9289. Min Act: -0.1700
Data Index: 5934683 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9289. Min Act: -0.1700
Data Index: 4926771 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9374. Min Act: -0.1700
Data Index: 7869113 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9289. Min Act: -0.1700
Data Index: 7973996 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9289. Min Act: -0.1700
Data Index: 3353881 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9374. Min Act: -0.1700
Data Index: 8511338 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0136. Min Range: -2.0136
Max Act: 1.9204. Min Act: -0.1700
Data Index: 7196320 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19