Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5548 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2337. Min Range: -5.2337
Max Act: 5.2337. Min Act: -0.1700
Data Index: 418901 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2337. Min Range: -5.2337
Max Act: 5.2337. Min Act: -0.1700
Data Index: 3504725 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2337. Min Range: -5.2337
Max Act: 5.2024. Min Act: -0.1700
Data Index: 5169415 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2337. Min Range: -5.2337
Max Act: 5.1712. Min Act: -0.1700
Data Index: 660754 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2337. Min Range: -5.2337
Max Act: 5.0149. Min Act: -0.1700
Data Index: 4626434 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2337. Min Range: -5.2337
Max Act: 4.9837. Min Act: -0.1700
Data Index: 351478 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2337. Min Range: -5.2337
Max Act: 4.9524. Min Act: -0.1700
Data Index: 6875894 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2337. Min Range: -5.2337
Max Act: 4.9212. Min Act: -0.1700
Data Index: 6870845 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2337. Min Range: -5.2337
Max Act: 4.9212. Min Act: -0.1700
Data Index: 4464175 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2337. Min Range: -5.2337
Max Act: 4.8899. Min Act: -0.1700
Data Index: 699076 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2337. Min Range: -5.2337
Max Act: 4.8899. Min Act: -0.1700
Data Index: 3807443 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2337. Min Range: -5.2337
Max Act: 4.8899. Min Act: -0.1700
Data Index: 3676827 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2337. Min Range: -5.2337
Max Act: 4.8899. Min Act: -0.1700
Data Index: 1305076 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2337. Min Range: -5.2337
Max Act: 4.8587. Min Act: -0.1700
Data Index: 7916476 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2337. Min Range: -5.2337
Max Act: 4.8274. Min Act: -0.1700
Data Index: 5364534 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2337. Min Range: -5.2337
Max Act: 4.8587. Min Act: -0.1700
Data Index: 4403863 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2337. Min Range: -5.2337
Max Act: 4.8274. Min Act: -0.1700
Data Index: 2950010 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2337. Min Range: -5.2337
Max Act: 4.8274. Min Act: -0.1700
Data Index: 4822092 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2337. Min Range: -5.2337
Max Act: 4.7962. Min Act: -0.1700
Data Index: 984840 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2337. Min Range: -5.2337
Max Act: 4.7962. Min Act: -0.1700
Data Index: 7530210 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19