Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3853 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.8425. Min Act: -0.1700
Data Index: 8488801 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.8738. Min Act: -0.1700
Data Index: 4143271 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.7800. Min Act: -0.1700
Data Index: 4537710 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.7488. Min Act: -0.1700
Data Index: 4143272 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.7800. Min Act: -0.1700
Data Index: 4223956 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.7488. Min Act: -0.1700
Data Index: 1831544 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.7175. Min Act: -0.1700
Data Index: 8005800 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.6863. Min Act: -0.1700
Data Index: 472457 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.6863. Min Act: -0.1700
Data Index: 4013781 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.6550. Min Act: -0.1700
Data Index: 4376585 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.6550. Min Act: -0.1700
Data Index: 3556716 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.6238. Min Act: -0.1700
Data Index: 6894941 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.6550. Min Act: -0.1700
Data Index: 3715251 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.5925. Min Act: -0.1700
Data Index: 1791703 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.5613. Min Act: -0.1700
Data Index: 92781 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.4988. Min Act: -0.1700
Data Index: 106096 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.5300. Min Act: -0.1700
Data Index: 5077073 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.5300. Min Act: -0.1700
Data Index: 1003672 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.5300. Min Act: -0.1700
Data Index: 1778658 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8738. Min Range: -4.8738
Max Act: 4.4988. Min Act: -0.1700
Data Index: 5112018 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19