Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3261 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0887. Min Range: -7.0887
Max Act: 7.0887. Min Act: -0.1700
Data Index: 407373 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.7137. Min Act: -0.1700
Data Index: 8017449 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.7449. Min Act: -0.1700
Data Index: 2074587 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.5887. Min Act: -0.1700
Data Index: 7899525 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.6199. Min Act: -0.1700
Data Index: 2577429 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.6199. Min Act: -0.1700
Data Index: 5555621 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.5574. Min Act: -0.1700
Data Index: 1637271 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.5262. Min Act: -0.1700
Data Index: 650235 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.5262. Min Act: -0.1700
Data Index: 3550558 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.4949. Min Act: -0.1700
Data Index: 7052165 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.4949. Min Act: -0.1700
Data Index: 3170170 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.4637. Min Act: -0.1700
Data Index: 1438453 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.4637. Min Act: -0.1700
Data Index: 3255527 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.4012. Min Act: -0.1700
Data Index: 6497315 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.4324. Min Act: -0.1700
Data Index: 8236691 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.4012. Min Act: -0.1700
Data Index: 814125 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.3387. Min Act: -0.1700
Data Index: 4553220 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.3699. Min Act: -0.1700
Data Index: 1735672 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.3699. Min Act: -0.1700
Data Index: 1980798 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0887. Min Range: -7.0887
Max Act: 6.3699. Min Act: -0.1700
Data Index: 1600410 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19