Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3627 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3394. Min Range: -4.3394
Max Act: 4.3394. Min Act: -0.1700
Data Index: 6768460 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3394. Min Range: -4.3394
Max Act: 4.2144. Min Act: -0.1700
Data Index: 7014562 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3394. Min Range: -4.3394
Max Act: 4.1519. Min Act: -0.1700
Data Index: 3218954 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3394. Min Range: -4.3394
Max Act: 4.0894. Min Act: -0.1700
Data Index: 1617840 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3394. Min Range: -4.3394
Max Act: 4.0581. Min Act: -0.1700
Data Index: 6003282 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3394. Min Range: -4.3394
Max Act: 4.0894. Min Act: -0.1700
Data Index: 25109 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3394. Min Range: -4.3394
Max Act: 4.0894. Min Act: -0.1700
Data Index: 5190318 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3394. Min Range: -4.3394
Max Act: 4.1206. Min Act: -0.1700
Data Index: 7380791 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3394. Min Range: -4.3394
Max Act: 4.0894. Min Act: -0.1700
Data Index: 6408653 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3394. Min Range: -4.3394
Max Act: 4.0581. Min Act: -0.1700
Data Index: 6103340 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3394. Min Range: -4.3394
Max Act: 4.0581. Min Act: -0.1700
Data Index: 2923596 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3394. Min Range: -4.3394
Max Act: 4.0581. Min Act: -0.1700
Data Index: 43650 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3394. Min Range: -4.3394
Max Act: 4.0581. Min Act: -0.1700
Data Index: 4478133 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3394. Min Range: -4.3394
Max Act: 4.0581. Min Act: -0.1700
Data Index: 4997555 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3394. Min Range: -4.3394
Max Act: 4.0581. Min Act: -0.1700
Data Index: 602740 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3394. Min Range: -4.3394
Max Act: 4.0269. Min Act: -0.1700
Data Index: 2845481 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3394. Min Range: -4.3394
Max Act: 4.0269. Min Act: -0.1700
Data Index: 8182007 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3394. Min Range: -4.3394
Max Act: 4.0269. Min Act: -0.1700
Data Index: 8640687 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3394. Min Range: -4.3394
Max Act: 3.9956. Min Act: -0.1700
Data Index: 4348522 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3394. Min Range: -4.3394
Max Act: 3.9956. Min Act: -0.1700
Data Index: 4657936 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19