Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1653 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3656. Min Range: -5.3656
Max Act: 5.3656. Min Act: -0.1700
Data Index: 2289269 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3656. Min Range: -5.3656
Max Act: 5.2093. Min Act: -0.1700
Data Index: 212315 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3656. Min Range: -5.3656
Max Act: 5.0843. Min Act: -0.1700
Data Index: 5696737 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3656. Min Range: -5.3656
Max Act: 5.0531. Min Act: -0.1700
Data Index: 6109304 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3656. Min Range: -5.3656
Max Act: 5.0218. Min Act: -0.1700
Data Index: 8787856 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3656. Min Range: -5.3656
Max Act: 4.9906. Min Act: -0.1700
Data Index: 8007255 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3656. Min Range: -5.3656
Max Act: 4.9906. Min Act: -0.1700
Data Index: 2195596 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3656. Min Range: -5.3656
Max Act: 4.9593. Min Act: -0.1700
Data Index: 532659 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3656. Min Range: -5.3656
Max Act: 4.9281. Min Act: -0.1700
Data Index: 5414169 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3656. Min Range: -5.3656
Max Act: 4.8656. Min Act: -0.1700
Data Index: 376514 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3656. Min Range: -5.3656
Max Act: 4.8656. Min Act: -0.1700
Data Index: 4944110 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3656. Min Range: -5.3656
Max Act: 4.8968. Min Act: -0.1700
Data Index: 5114421 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3656. Min Range: -5.3656
Max Act: 4.8656. Min Act: -0.1700
Data Index: 1446731 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3656. Min Range: -5.3656
Max Act: 4.8656. Min Act: -0.1700
Data Index: 5706904 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3656. Min Range: -5.3656
Max Act: 4.8656. Min Act: -0.1700
Data Index: 2208673 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3656. Min Range: -5.3656
Max Act: 4.8031. Min Act: -0.1700
Data Index: 7127664 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3656. Min Range: -5.3656
Max Act: 4.8343. Min Act: -0.1700
Data Index: 1539811 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3656. Min Range: -5.3656
Max Act: 4.8343. Min Act: -0.1700
Data Index: 7497679 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3656. Min Range: -5.3656
Max Act: 4.8343. Min Act: -0.1700
Data Index: 6837865 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3656. Min Range: -5.3656
Max Act: 4.8031. Min Act: -0.1700
Data Index: 5627754 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19