Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.6636. Min Act: -0.1700
Data Index: 8707228 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.5385. Min Act: -0.1700
Data Index: 5875225 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.5073. Min Act: -0.1700
Data Index: 5959429 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.4135. Min Act: -0.1700
Data Index: 5037852 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.4135. Min Act: -0.1700
Data Index: 4379300 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.3198. Min Act: -0.1700
Data Index: 6107951 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.3198. Min Act: -0.1700
Data Index: 4620840 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.2885. Min Act: -0.1700
Data Index: 7060908 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.2885. Min Act: -0.1700
Data Index: 6255856 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.2573. Min Act: -0.1700
Data Index: 5284642 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.2573. Min Act: -0.1700
Data Index: 6519702 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.2573. Min Act: -0.1700
Data Index: 6206286 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.2573. Min Act: -0.1700
Data Index: 5872245 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.2573. Min Act: -0.1700
Data Index: 3263543 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.2260. Min Act: -0.1700
Data Index: 2742473 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.2260. Min Act: -0.1700
Data Index: 6450782 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.2260. Min Act: -0.1700
Data Index: 2132334 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.2260. Min Act: -0.1700
Data Index: 3628812 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.2260. Min Act: -0.1700
Data Index: 7149521 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6636. Min Range: -4.6636
Max Act: 4.2260. Min Act: -0.1700
Data Index: 5513689 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19