Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5468 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.8521. Min Act: -0.1700
Data Index: 6899388 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.6959. Min Act: -0.1700
Data Index: 7535440 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.6646. Min Act: -0.1700
Data Index: 5876933 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.6959. Min Act: -0.1700
Data Index: 2379788 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.6334. Min Act: -0.1700
Data Index: 5994289 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.6334. Min Act: -0.1700
Data Index: 7649581 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.6646. Min Act: -0.1700
Data Index: 686446 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.6334. Min Act: -0.1700
Data Index: 5994288 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.6021. Min Act: -0.1700
Data Index: 8296574 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.5709. Min Act: -0.1700
Data Index: 5699722 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.5396. Min Act: -0.1700
Data Index: 1792776 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.5084. Min Act: -0.1700
Data Index: 8759557 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.5084. Min Act: -0.1700
Data Index: 2223809 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.4771. Min Act: -0.1700
Data Index: 6985507 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.4771. Min Act: -0.1700
Data Index: 8310311 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.5084. Min Act: -0.1700
Data Index: 4287111 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.4771. Min Act: -0.1700
Data Index: 6655769 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.4459. Min Act: -0.1700
Data Index: 5030370 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.4459. Min Act: -0.1700
Data Index: 4081357 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8521. Min Range: -5.8521
Max Act: 5.4459. Min Act: -0.1700
Data Index: 6166920 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19