Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3207 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0478. Min Range: -5.0478
Max Act: 5.0478. Min Act: -0.1700
Data Index: 4968677 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.9228. Min Act: -0.1700
Data Index: 8374888 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.9228. Min Act: -0.1700
Data Index: 8374881 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.8291. Min Act: -0.1700
Data Index: 6056677 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.8291. Min Act: -0.1700
Data Index: 2727900 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7978. Min Act: -0.1700
Data Index: 7133812 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7666. Min Act: -0.1700
Data Index: 4358830 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7041. Min Act: -0.1700
Data Index: 1592602 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7353. Min Act: -0.1700
Data Index: 5937030 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7041. Min Act: -0.1700
Data Index: 2727904 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7041. Min Act: -0.1700
Data Index: 4968675 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7041. Min Act: -0.1700
Data Index: 442268 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7041. Min Act: -0.1700
Data Index: 6763118 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.6728. Min Act: -0.1700
Data Index: 2727910 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.6728. Min Act: -0.1700
Data Index: 2733162 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.6728. Min Act: -0.1700
Data Index: 6060833 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.6728. Min Act: -0.1700
Data Index: 6763117 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.6728. Min Act: -0.1700
Data Index: 8678251 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.6728. Min Act: -0.1700
Data Index: 5937027 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.6416. Min Act: -0.1700
Data Index: 1592601 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19