Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3159 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.9765. Min Act: -0.1700
Data Index: 1666024 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.9452. Min Act: -0.1700
Data Index: 8258488 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.9452. Min Act: -0.1700
Data Index: 3671801 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.8670. Min Act: -0.1700
Data Index: 1439015 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.8358. Min Act: -0.1700
Data Index: 7955303 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.7888. Min Act: -0.1700
Data Index: 6011422 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.7888. Min Act: -0.1700
Data Index: 7257448 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.7732. Min Act: -0.1700
Data Index: 6505562 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.7576. Min Act: -0.1700
Data Index: 3614020 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.7419. Min Act: -0.1700
Data Index: 5709386 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.7107. Min Act: -0.1700
Data Index: 7203533 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.6950. Min Act: -0.1700
Data Index: 5911752 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.6794. Min Act: -0.1700
Data Index: 6836400 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.6637. Min Act: -0.1700
Data Index: 7935773 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.6481. Min Act: -0.1700
Data Index: 7179916 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.6481. Min Act: -0.1700
Data Index: 1483813 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.6481. Min Act: -0.1700
Data Index: 923132 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.6324. Min Act: -0.1700
Data Index: 1085660 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.6481. Min Act: -0.1700
Data Index: 2801467 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9765. Min Range: -3.9765
Max Act: 3.6324. Min Act: -0.1700
Data Index: 3372645 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19