Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5019 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4125. Min Range: -4.4125
Max Act: 4.4125. Min Act: -0.1700
Data Index: 3254978 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4125. Min Range: -4.4125
Max Act: 4.4125. Min Act: -0.1700
Data Index: 3254976 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4125. Min Range: -4.4125
Max Act: 4.2875. Min Act: -0.1700
Data Index: 2561018 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4125. Min Range: -4.4125
Max Act: 4.1937. Min Act: -0.1700
Data Index: 677764 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4125. Min Range: -4.4125
Max Act: 4.1312. Min Act: -0.1700
Data Index: 8467311 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4125. Min Range: -4.4125
Max Act: 4.1937. Min Act: -0.1700
Data Index: 8210120 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4125. Min Range: -4.4125
Max Act: 4.1312. Min Act: -0.1700
Data Index: 6762140 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4125. Min Range: -4.4125
Max Act: 4.1625. Min Act: -0.1700
Data Index: 4894087 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4125. Min Range: -4.4125
Max Act: 4.1312. Min Act: -0.1700
Data Index: 7110745 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4125. Min Range: -4.4125
Max Act: 4.1000. Min Act: -0.1700
Data Index: 2458687 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4125. Min Range: -4.4125
Max Act: 4.0687. Min Act: -0.1700
Data Index: 801759 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4125. Min Range: -4.4125
Max Act: 4.0375. Min Act: -0.1700
Data Index: 1527136 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4125. Min Range: -4.4125
Max Act: 4.0062. Min Act: -0.1700
Data Index: 3261660 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4125. Min Range: -4.4125
Max Act: 4.0062. Min Act: -0.1700
Data Index: 4688460 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4125. Min Range: -4.4125
Max Act: 4.0062. Min Act: -0.1700
Data Index: 7782640 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4125. Min Range: -4.4125
Max Act: 4.0062. Min Act: -0.1700
Data Index: 1307631 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4125. Min Range: -4.4125
Max Act: 4.0062. Min Act: -0.1700
Data Index: 6332615 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4125. Min Range: -4.4125
Max Act: 3.9749. Min Act: -0.1700
Data Index: 1517926 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4125. Min Range: -4.4125
Max Act: 3.9749. Min Act: -0.1700
Data Index: 291254 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4125. Min Range: -4.4125
Max Act: 3.9749. Min Act: -0.1700
Data Index: 4631098 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19