Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1865 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4220. Min Range: -6.4220
Max Act: 6.4220. Min Act: -0.1700
Data Index: 3152898 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4220. Min Range: -6.4220
Max Act: 6.3595. Min Act: -0.1700
Data Index: 3224949 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4220. Min Range: -6.4220
Max Act: 6.3283. Min Act: -0.1700
Data Index: 319469 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4220. Min Range: -6.4220
Max Act: 6.2658. Min Act: -0.1700
Data Index: 7468502 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4220. Min Range: -6.4220
Max Act: 6.2345. Min Act: -0.1700
Data Index: 7724646 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4220. Min Range: -6.4220
Max Act: 6.2345. Min Act: -0.1700
Data Index: 7322955 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4220. Min Range: -6.4220
Max Act: 6.2345. Min Act: -0.1700
Data Index: 6312479 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4220. Min Range: -6.4220
Max Act: 6.2345. Min Act: -0.1700
Data Index: 3244979 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4220. Min Range: -6.4220
Max Act: 6.2033. Min Act: -0.1700
Data Index: 4502090 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4220. Min Range: -6.4220
Max Act: 6.1720. Min Act: -0.1700
Data Index: 4778545 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4220. Min Range: -6.4220
Max Act: 6.0470. Min Act: -0.1700
Data Index: 5806924 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4220. Min Range: -6.4220
Max Act: 6.0470. Min Act: -0.1700
Data Index: 4500206 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4220. Min Range: -6.4220
Max Act: 6.0158. Min Act: -0.1700
Data Index: 6869461 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4220. Min Range: -6.4220
Max Act: 5.9533. Min Act: -0.1700
Data Index: 8604939 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4220. Min Range: -6.4220
Max Act: 5.9533. Min Act: -0.1700
Data Index: 5084621 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4220. Min Range: -6.4220
Max Act: 5.9533. Min Act: -0.1700
Data Index: 3369487 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4220. Min Range: -6.4220
Max Act: 5.9220. Min Act: -0.1700
Data Index: 2397247 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4220. Min Range: -6.4220
Max Act: 5.8908. Min Act: -0.1700
Data Index: 3348605 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4220. Min Range: -6.4220
Max Act: 5.8908. Min Act: -0.1700
Data Index: 2181330 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4220. Min Range: -6.4220
Max Act: 5.8908. Min Act: -0.1700
Data Index: 1051511 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19