Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3485 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.9037. Min Act: -0.1700
Data Index: 6094376 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.8412. Min Act: -0.1700
Data Index: 7966349 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.8100. Min Act: -0.1700
Data Index: 7457220 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.7475. Min Act: -0.1700
Data Index: 1885194 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.7475. Min Act: -0.1700
Data Index: 4614987 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.6850. Min Act: -0.1700
Data Index: 5328397 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.6850. Min Act: -0.1700
Data Index: 8809987 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.6537. Min Act: -0.1700
Data Index: 6950664 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.6850. Min Act: -0.1700
Data Index: 2151114 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.6225. Min Act: -0.1700
Data Index: 3831565 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.6537. Min Act: -0.1700
Data Index: 8470283 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.5912. Min Act: -0.1700
Data Index: 1950528 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.6225. Min Act: -0.1700
Data Index: 4472457 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.6225. Min Act: -0.1700
Data Index: 3257432 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.6225. Min Act: -0.1700
Data Index: 984895 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.6225. Min Act: -0.1700
Data Index: 43214 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.5912. Min Act: -0.1700
Data Index: 7002698 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.5912. Min Act: -0.1700
Data Index: 1388682 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.5912. Min Act: -0.1700
Data Index: 4147727 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9037. Min Range: -5.9037
Max Act: 5.5912. Min Act: -0.1700
Data Index: 8208989 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19