Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3214 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.7764. Min Act: -0.1700
Data Index: 6653672 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.7138. Min Act: -0.1700
Data Index: 1905839 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.6982. Min Act: -0.1700
Data Index: 5638490 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.6356. Min Act: -0.1700
Data Index: 7394143 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.6199. Min Act: -0.1700
Data Index: 5092205 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.6043. Min Act: -0.1700
Data Index: 2285520 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.5417. Min Act: -0.1700
Data Index: 1250457 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.5573. Min Act: -0.1700
Data Index: 212675 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.5260. Min Act: -0.1700
Data Index: 6267487 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.5104. Min Act: -0.1700
Data Index: 1469648 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.5104. Min Act: -0.1700
Data Index: 2641871 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.4947. Min Act: -0.1700
Data Index: 1099563 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.5104. Min Act: -0.1700
Data Index: 2510134 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.4790. Min Act: -0.1700
Data Index: 3396503 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.4477. Min Act: -0.1700
Data Index: 234074 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.4477. Min Act: -0.1700
Data Index: 6921286 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.4320. Min Act: -0.1700
Data Index: 1038863 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.4320. Min Act: -0.1700
Data Index: 6237866 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.4163. Min Act: -0.1700
Data Index: 7454672 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7764. Min Range: -3.7764
Max Act: 3.4163. Min Act: -0.1700
Data Index: 5842385 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19