Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1331 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.5796. Min Act: -0.1697
Data Index: 315039 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.5409. Min Act: -0.1700
Data Index: 8121528 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.5409. Min Act: -0.1700
Data Index: 3467342 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.5029. Min Act: -0.1700
Data Index: 6880999 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.5029. Min Act: -0.1700
Data Index: 4498057 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.4879. Min Act: -0.1699
Data Index: 2874442 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.4879. Min Act: -0.1700
Data Index: 3066558 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.4731. Min Act: -0.1696
Data Index: 1218062 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.4805. Min Act: -0.1700
Data Index: 2788103 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.4583. Min Act: -0.1700
Data Index: 5181619 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.4583. Min Act: -0.1700
Data Index: 5860137 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.4583. Min Act: -0.1691
Data Index: 1555340 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.4583. Min Act: -0.1700
Data Index: 594905 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.4510. Min Act: -0.1700
Data Index: 7720132 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.4365. Min Act: -0.1700
Data Index: 5549655 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.4365. Min Act: -0.1700
Data Index: 2175779 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.4510. Min Act: -0.1697
Data Index: 8322928 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.4510. Min Act: -0.1700
Data Index: 8203147 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.4437. Min Act: -0.1700
Data Index: 1143960 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5796. Min Range: -0.5796
Max Act: 0.4149. Min Act: -0.1700
Data Index: 4018156 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19