Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4026 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1324. Min Range: -6.1324
Max Act: 6.1324. Min Act: -0.1700
Data Index: 7339571 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1324. Min Range: -6.1324
Max Act: 6.0386. Min Act: -0.1700
Data Index: 4237921 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1324. Min Range: -6.1324
Max Act: 5.9449. Min Act: -0.1700
Data Index: 6396296 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1324. Min Range: -6.1324
Max Act: 5.9136. Min Act: -0.1700
Data Index: 4372993 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1324. Min Range: -6.1324
Max Act: 5.8824. Min Act: -0.1700
Data Index: 3481978 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1324. Min Range: -6.1324
Max Act: 5.8824. Min Act: -0.1700
Data Index: 5227985 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1324. Min Range: -6.1324
Max Act: 5.8824. Min Act: -0.1700
Data Index: 7266647 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1324. Min Range: -6.1324
Max Act: 5.8511. Min Act: -0.1700
Data Index: 6409430 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1324. Min Range: -6.1324
Max Act: 5.8511. Min Act: -0.1700
Data Index: 8672386 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1324. Min Range: -6.1324
Max Act: 5.8199. Min Act: -0.1700
Data Index: 3824577 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1324. Min Range: -6.1324
Max Act: 5.7886. Min Act: -0.1700
Data Index: 2581047 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1324. Min Range: -6.1324
Max Act: 5.7574. Min Act: -0.1700
Data Index: 1728858 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1324. Min Range: -6.1324
Max Act: 5.7886. Min Act: -0.1700
Data Index: 7576786 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1324. Min Range: -6.1324
Max Act: 5.7886. Min Act: -0.1700
Data Index: 7927071 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1324. Min Range: -6.1324
Max Act: 5.7886. Min Act: -0.1700
Data Index: 3925015 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1324. Min Range: -6.1324
Max Act: 5.7574. Min Act: -0.1700
Data Index: 743323 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1324. Min Range: -6.1324
Max Act: 5.7574. Min Act: -0.1700
Data Index: 3014653 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1324. Min Range: -6.1324
Max Act: 5.7886. Min Act: -0.1700
Data Index: 5271390 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1324. Min Range: -6.1324
Max Act: 5.7574. Min Act: -0.1700
Data Index: 6838032 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1324. Min Range: -6.1324
Max Act: 5.7261. Min Act: -0.1700
Data Index: 6687853 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19