Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4944 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.7967. Min Act: -0.1700
Data Index: 1720072 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.7169. Min Act: -0.1700
Data Index: 8762072 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.6689. Min Act: -0.1700
Data Index: 8273104 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.6528. Min Act: -0.1700
Data Index: 7217107 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.6368. Min Act: -0.1700
Data Index: 6229352 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.6368. Min Act: -0.1700
Data Index: 4740234 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.6368. Min Act: -0.1700
Data Index: 8507414 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.6207. Min Act: -0.1700
Data Index: 5671577 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.6046. Min Act: -0.1700
Data Index: 7216134 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.6046. Min Act: -0.1700
Data Index: 739626 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.5886. Min Act: -0.1700
Data Index: 6715145 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.5886. Min Act: -0.1700
Data Index: 7369542 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.5724. Min Act: -0.1700
Data Index: 2216450 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.5724. Min Act: -0.1700
Data Index: 5583203 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.5886. Min Act: -0.1700
Data Index: 8815211 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.5563. Min Act: -0.1700
Data Index: 438501 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.5563. Min Act: -0.1700
Data Index: 160798 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.5402. Min Act: -0.1700
Data Index: 6502806 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.5240. Min Act: -0.1700
Data Index: 3194082 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.5563. Min Act: -0.1700
Data Index: 3671234 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19