Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3652 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.7544. Min Act: -0.1700
Data Index: 1223339 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.6919. Min Act: -0.1700
Data Index: 2786966 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.6919. Min Act: -0.1700
Data Index: 6201187 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.6606. Min Act: -0.1700
Data Index: 1103096 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.4419. Min Act: -0.1700
Data Index: 1103097 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.4106. Min Act: -0.1700
Data Index: 4419465 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.3481. Min Act: -0.1700
Data Index: 3766378 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.3481. Min Act: -0.1700
Data Index: 940427 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.3481. Min Act: -0.1700
Data Index: 2264226 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.3169. Min Act: -0.1700
Data Index: 6718391 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.2856. Min Act: -0.1700
Data Index: 2941802 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.2856. Min Act: -0.1700
Data Index: 7659728 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.2856. Min Act: -0.1700
Data Index: 5584674 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.2856. Min Act: -0.1700
Data Index: 3121482 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.2231. Min Act: -0.1700
Data Index: 7385727 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.2544. Min Act: -0.1700
Data Index: 7462915 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.2544. Min Act: -0.1700
Data Index: 2264228 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.2544. Min Act: -0.1700
Data Index: 44800 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.2231. Min Act: -0.1700
Data Index: 1304355 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7544. Min Range: -5.7544
Max Act: 5.2231. Min Act: -0.1700
Data Index: 2629902 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19