Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3155 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.7720. Min Act: -0.1700
Data Index: 8256211 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.7407. Min Act: -0.1700
Data Index: 8227332 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.7095. Min Act: -0.1700
Data Index: 7089837 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.7095. Min Act: -0.1700
Data Index: 226032 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.6782. Min Act: -0.1700
Data Index: 7123498 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.6782. Min Act: -0.1700
Data Index: 783301 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.6782. Min Act: -0.1700
Data Index: 7003566 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.6470. Min Act: -0.1700
Data Index: 683533 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.6782. Min Act: -0.1700
Data Index: 5124802 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.6470. Min Act: -0.1700
Data Index: 3681767 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.6470. Min Act: -0.1700
Data Index: 8302838 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.6157. Min Act: -0.1700
Data Index: 7683360 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.6157. Min Act: -0.1700
Data Index: 7958744 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.6157. Min Act: -0.1700
Data Index: 2567663 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.6157. Min Act: -0.1700
Data Index: 2264395 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.6157. Min Act: -0.1700
Data Index: 5787651 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.5845. Min Act: -0.1700
Data Index: 2644790 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.5845. Min Act: -0.1700
Data Index: 7135927 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.5845. Min Act: -0.1700
Data Index: 1313477 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7720. Min Range: -4.7720
Max Act: 4.5845. Min Act: -0.1700
Data Index: 5569582 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19