Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3264 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3606. Min Range: -7.3606
Max Act: 7.3606. Min Act: -0.1700
Data Index: 1123771 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3606. Min Range: -7.3606
Max Act: 7.3606. Min Act: -0.1700
Data Index: 1003103 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3606. Min Range: -7.3606
Max Act: 7.2981. Min Act: -0.1700
Data Index: 6850203 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3606. Min Range: -7.3606
Max Act: 7.2669. Min Act: -0.1700
Data Index: 2642066 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3606. Min Range: -7.3606
Max Act: 7.2044. Min Act: -0.1700
Data Index: 3693218 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3606. Min Range: -7.3606
Max Act: 7.1419. Min Act: -0.1700
Data Index: 7805023 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3606. Min Range: -7.3606
Max Act: 7.1419. Min Act: -0.1700
Data Index: 5530855 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3606. Min Range: -7.3606
Max Act: 7.1106. Min Act: -0.1700
Data Index: 5662165 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3606. Min Range: -7.3606
Max Act: 7.0169. Min Act: -0.1700
Data Index: 7290072 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3606. Min Range: -7.3606
Max Act: 7.0169. Min Act: -0.1700
Data Index: 5276271 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.9856. Min Act: -0.1700
Data Index: 2229916 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.9856. Min Act: -0.1700
Data Index: 1255558 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.9856. Min Act: -0.1700
Data Index: 4283942 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.9231. Min Act: -0.1700
Data Index: 4913166 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.9231. Min Act: -0.1700
Data Index: 6155569 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.8919. Min Act: -0.1700
Data Index: 5423856 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.8919. Min Act: -0.1700
Data Index: 3412673 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.8919. Min Act: -0.1700
Data Index: 735572 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.8919. Min Act: -0.1700
Data Index: 4869470 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.8919. Min Act: -0.1700
Data Index: 6322028 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19