Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5136 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.9278. Min Act: -0.1700
Data Index: 859194 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.8965. Min Act: -0.1700
Data Index: 5405094 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.8965. Min Act: -0.1700
Data Index: 5154909 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.8653. Min Act: -0.1700
Data Index: 859195 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.8653. Min Act: -0.1700
Data Index: 5405093 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.8653. Min Act: -0.1700
Data Index: 1781002 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.8340. Min Act: -0.1700
Data Index: 3271877 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.8028. Min Act: -0.1700
Data Index: 3213646 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.8028. Min Act: -0.1700
Data Index: 6607165 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.8028. Min Act: -0.1700
Data Index: 6676944 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.7715. Min Act: -0.1700
Data Index: 8335133 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.7090. Min Act: -0.1700
Data Index: 5577967 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.7090. Min Act: -0.1700
Data Index: 6615460 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.7090. Min Act: -0.1700
Data Index: 1628864 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.7090. Min Act: -0.1700
Data Index: 8365691 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.7090. Min Act: -0.1700
Data Index: 850693 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.7090. Min Act: -0.1700
Data Index: 7544601 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.6778. Min Act: -0.1700
Data Index: 5849599 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.6778. Min Act: -0.1700
Data Index: 4541850 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9278. Min Range: -4.9278
Max Act: 4.6778. Min Act: -0.1700
Data Index: 7977663 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19