Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 766 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4536. Min Range: -7.4536
Max Act: 7.4536. Min Act: -0.1700
Data Index: 8675249 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4536. Min Range: -7.4536
Max Act: 7.3911. Min Act: -0.1700
Data Index: 2910984 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4536. Min Range: -7.4536
Max Act: 7.3286. Min Act: -0.1700
Data Index: 3749485 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4536. Min Range: -7.4536
Max Act: 7.1411. Min Act: -0.1700
Data Index: 5618056 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4536. Min Range: -7.4536
Max Act: 7.1411. Min Act: -0.1700
Data Index: 1851956 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4536. Min Range: -7.4536
Max Act: 7.0161. Min Act: -0.1700
Data Index: 3702493 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4536. Min Range: -7.4536
Max Act: 6.9849. Min Act: -0.1700
Data Index: 6722694 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4536. Min Range: -7.4536
Max Act: 6.8911. Min Act: -0.1700
Data Index: 3696994 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4536. Min Range: -7.4536
Max Act: 6.7661. Min Act: -0.1700
Data Index: 4915289 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4536. Min Range: -7.4536
Max Act: 6.7661. Min Act: -0.1700
Data Index: 4701533 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4536. Min Range: -7.4536
Max Act: 6.7349. Min Act: -0.1700
Data Index: 4066667 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4536. Min Range: -7.4536
Max Act: 6.7036. Min Act: -0.1700
Data Index: 3521542 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4536. Min Range: -7.4536
Max Act: 6.7036. Min Act: -0.1700
Data Index: 445028 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4536. Min Range: -7.4536
Max Act: 6.6724. Min Act: -0.1700
Data Index: 3903345 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4536. Min Range: -7.4536
Max Act: 6.6724. Min Act: -0.1700
Data Index: 8027521 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4536. Min Range: -7.4536
Max Act: 6.6724. Min Act: -0.1700
Data Index: 6795069 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4536. Min Range: -7.4536
Max Act: 6.6411. Min Act: -0.1700
Data Index: 4665567 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4536. Min Range: -7.4536
Max Act: 6.6099. Min Act: -0.1700
Data Index: 1279715 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4536. Min Range: -7.4536
Max Act: 6.6099. Min Act: -0.1700
Data Index: 5302341 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4536. Min Range: -7.4536
Max Act: 6.6099. Min Act: -0.1700
Data Index: 3206357 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19