Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4257 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.5899. Min Act: -0.1698
Data Index: 6238869 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.5738. Min Act: -0.1700
Data Index: 4063525 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.5092. Min Act: -0.1697
Data Index: 1742128 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.4443. Min Act: -0.1700
Data Index: 7287761 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.4606. Min Act: -0.1638
Data Index: 480170 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.4280. Min Act: -0.1700
Data Index: 5768690 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.4443. Min Act: -0.1700
Data Index: 7433379 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.4280. Min Act: -0.1698
Data Index: 6884639 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.3954. Min Act: -0.1700
Data Index: 2848676 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.4117. Min Act: -0.1698
Data Index: 5019605 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.4117. Min Act: -0.1696
Data Index: 7004846 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.3627. Min Act: -0.1697
Data Index: 1992819 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.3791. Min Act: -0.1630
Data Index: 2673224 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.3954. Min Act: -0.1700
Data Index: 3149519 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.3791. Min Act: -0.1700
Data Index: 8135078 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.4117. Min Act: -0.1689
Data Index: 837266 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.3791. Min Act: -0.1700
Data Index: 1007164 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.3791. Min Act: -0.1700
Data Index: 3429199 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.3791. Min Act: -0.1686
Data Index: 4978416 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5899. Min Range: -2.5899
Max Act: 2.3791. Min Act: -0.1700
Data Index: 3045249 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19