Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.9594. Min Act: -0.1700
Data Index: 2422255 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.9281. Min Act: -0.1700
Data Index: 450439 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.8969. Min Act: -0.1700
Data Index: 1034111 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.8969. Min Act: -0.1700
Data Index: 751490 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.8969. Min Act: -0.1700
Data Index: 8560333 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.8656. Min Act: -0.1700
Data Index: 2042956 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.8656. Min Act: -0.1700
Data Index: 5617354 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.8656. Min Act: -0.1700
Data Index: 5582632 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.8656. Min Act: -0.1700
Data Index: 1963103 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.8656. Min Act: -0.1700
Data Index: 4708491 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.8656. Min Act: -0.1700
Data Index: 300288 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.8656. Min Act: -0.1700
Data Index: 1439907 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.8656. Min Act: -0.1700
Data Index: 8045639 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.8656. Min Act: -0.1700
Data Index: 6467960 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.8656. Min Act: -0.1700
Data Index: 3112755 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.8343. Min Act: -0.1700
Data Index: 1569660 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.8343. Min Act: -0.1700
Data Index: 2803619 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.8343. Min Act: -0.1700
Data Index: 5326097 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.8343. Min Act: -0.1700
Data Index: 2897423 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9594. Min Range: -3.9594
Max Act: 3.8343. Min Act: -0.1700
Data Index: 5858533 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19