Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2254 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.1569. Min Act: -0.1700
Data Index: 4702108 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.0944. Min Act: -0.1700
Data Index: 1761124 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.0319. Min Act: -0.1700
Data Index: 5910506 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.0319. Min Act: -0.1700
Data Index: 652073 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.0319. Min Act: -0.1700
Data Index: 6119712 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.0319. Min Act: -0.1700
Data Index: 7086085 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.0007. Min Act: -0.1700
Data Index: 5572132 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.9694. Min Act: -0.1700
Data Index: 8135002 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.9694. Min Act: -0.1700
Data Index: 7324693 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.8757. Min Act: -0.1700
Data Index: 874005 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.7819. Min Act: -0.1700
Data Index: 7364979 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.8132. Min Act: -0.1700
Data Index: 4918146 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.7819. Min Act: -0.1700
Data Index: 5767051 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.7819. Min Act: -0.1700
Data Index: 619972 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.7507. Min Act: -0.1700
Data Index: 2819502 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.7507. Min Act: -0.1700
Data Index: 6060729 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.7194. Min Act: -0.1700
Data Index: 3473747 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.7194. Min Act: -0.1700
Data Index: 3921018 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.6882. Min Act: -0.1700
Data Index: 4715503 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.6882. Min Act: -0.1700
Data Index: 4272009 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19