Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 526 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.6566. Min Act: -0.1700
Data Index: 301791 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.6566. Min Act: -0.1700
Data Index: 4651644 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.5629. Min Act: -0.1700
Data Index: 7036480 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.5004. Min Act: -0.1700
Data Index: 8642924 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.4691. Min Act: -0.1700
Data Index: 2478255 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.3754. Min Act: -0.1700
Data Index: 4850399 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.4379. Min Act: -0.1700
Data Index: 661027 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.3754. Min Act: -0.1700
Data Index: 3213038 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.3754. Min Act: -0.1700
Data Index: 5925844 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.3441. Min Act: -0.1700
Data Index: 6004493 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.3129. Min Act: -0.1700
Data Index: 7363576 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.3441. Min Act: -0.1700
Data Index: 551318 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.3441. Min Act: -0.1700
Data Index: 3581845 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.3441. Min Act: -0.1700
Data Index: 5142075 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.3441. Min Act: -0.1700
Data Index: 4797660 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.3129. Min Act: -0.1700
Data Index: 5239707 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.3441. Min Act: -0.1700
Data Index: 2865977 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.3129. Min Act: -0.1700
Data Index: 7021149 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.2816. Min Act: -0.1700
Data Index: 1500992 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6566. Min Range: -5.6566
Max Act: 5.3129. Min Act: -0.1700
Data Index: 366386 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19