Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2564 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7261. Min Range: -9.7261
Max Act: 9.7261. Min Act: -0.1700
Data Index: 5626665 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7261. Min Range: -9.7261
Max Act: 9.4761. Min Act: -0.1700
Data Index: 5377665 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7261. Min Range: -9.7261
Max Act: 9.3511. Min Act: -0.1700
Data Index: 3912186 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7261. Min Range: -9.7261
Max Act: 9.3511. Min Act: -0.1700
Data Index: 1514445 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7261. Min Range: -9.7261
Max Act: 9.2886. Min Act: -0.1700
Data Index: 4733676 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7261. Min Range: -9.7261
Max Act: 9.2261. Min Act: -0.1700
Data Index: 19959 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7261. Min Range: -9.7261
Max Act: 9.2886. Min Act: -0.1700
Data Index: 3339805 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7261. Min Range: -9.7261
Max Act: 9.1636. Min Act: -0.1700
Data Index: 3123137 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7261. Min Range: -9.7261
Max Act: 9.2261. Min Act: -0.1700
Data Index: 3720198 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7261. Min Range: -9.7261
Max Act: 9.2261. Min Act: -0.1700
Data Index: 8223414 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7261. Min Range: -9.7261
Max Act: 9.1636. Min Act: -0.1700
Data Index: 4209047 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7261. Min Range: -9.7261
Max Act: 9.1636. Min Act: -0.1700
Data Index: 4313212 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7261. Min Range: -9.7261
Max Act: 9.0386. Min Act: -0.1700
Data Index: 2665517 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7261. Min Range: -9.7261
Max Act: 9.0386. Min Act: -0.1700
Data Index: 1588568 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7261. Min Range: -9.7261
Max Act: 9.1011. Min Act: -0.1700
Data Index: 6269381 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7261. Min Range: -9.7261
Max Act: 9.0386. Min Act: -0.1700
Data Index: 3459242 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7261. Min Range: -9.7261
Max Act: 8.9761. Min Act: -0.1700
Data Index: 6674650 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7261. Min Range: -9.7261
Max Act: 8.9761. Min Act: -0.1700
Data Index: 3209709 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7261. Min Range: -9.7261
Max Act: 8.9761. Min Act: -0.1700
Data Index: 4810723 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7261. Min Range: -9.7261
Max Act: 8.9136. Min Act: -0.1700
Data Index: 1000506 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19