Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5958 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.3814. Min Act: -0.1700
Data Index: 1166233 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.3657. Min Act: -0.1700
Data Index: 1166234 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.3500. Min Act: -0.1700
Data Index: 8101150 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.3187. Min Act: -0.1700
Data Index: 2794989 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2716. Min Act: -0.1700
Data Index: 7106059 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2716. Min Act: -0.1700
Data Index: 6371182 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2401. Min Act: -0.1700
Data Index: 326100 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2244. Min Act: -0.1700
Data Index: 2651939 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2244. Min Act: -0.1700
Data Index: 5481669 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2244. Min Act: -0.1700
Data Index: 966334 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2244. Min Act: -0.1700
Data Index: 2001267 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2087. Min Act: -0.1700
Data Index: 3515475 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.1930. Min Act: -0.1700
Data Index: 2764700 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.1772. Min Act: -0.1700
Data Index: 209787 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.1772. Min Act: -0.1700
Data Index: 5899789 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.1772. Min Act: -0.1700
Data Index: 4516456 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.1772. Min Act: -0.1700
Data Index: 2425679 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.1615. Min Act: -0.1700
Data Index: 6249781 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.1458. Min Act: -0.1700
Data Index: 539373 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.1615. Min Act: -0.1700
Data Index: 4300457 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19