Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4815 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.4076. Min Act: -0.1700
Data Index: 3114501 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.3139. Min Act: -0.1700
Data Index: 5745121 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.2826. Min Act: -0.1700
Data Index: 3755546 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.2201. Min Act: -0.1700
Data Index: 2459091 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.1576. Min Act: -0.1700
Data Index: 3979763 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.1576. Min Act: -0.1700
Data Index: 5078955 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.1264. Min Act: -0.1700
Data Index: 5286013 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.0951. Min Act: -0.1700
Data Index: 5531461 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.1264. Min Act: -0.1700
Data Index: 8688620 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.0951. Min Act: -0.1700
Data Index: 8429802 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.0639. Min Act: -0.1700
Data Index: 2613240 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.0326. Min Act: -0.1700
Data Index: 3994076 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.0326. Min Act: -0.1700
Data Index: 5289570 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.0326. Min Act: -0.1700
Data Index: 6205207 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.0014. Min Act: -0.1700
Data Index: 5758696 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.0014. Min Act: -0.1700
Data Index: 7506836 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.0014. Min Act: -0.1700
Data Index: 2453176 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.0014. Min Act: -0.1700
Data Index: 8618621 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4076. Min Range: -6.4076
Max Act: 6.0014. Min Act: -0.1700
Data Index: 366324 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4076. Min Range: -6.4076
Max Act: 5.9701. Min Act: -0.1700
Data Index: 8363355 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19