Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1929 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5793. Min Range: -6.5793
Max Act: 6.5793. Min Act: -0.1700
Data Index: 5079124 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5793. Min Range: -6.5793
Max Act: 6.1418. Min Act: -0.1700
Data Index: 3436350 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5793. Min Range: -6.5793
Max Act: 6.1418. Min Act: -0.1700
Data Index: 1186616 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5793. Min Range: -6.5793
Max Act: 6.1106. Min Act: -0.1700
Data Index: 4391671 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5793. Min Range: -6.5793
Max Act: 6.0481. Min Act: -0.1700
Data Index: 4879728 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5793. Min Range: -6.5793
Max Act: 6.0481. Min Act: -0.1700
Data Index: 6494495 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5793. Min Range: -6.5793
Max Act: 6.0168. Min Act: -0.1700
Data Index: 334387 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5793. Min Range: -6.5793
Max Act: 6.0168. Min Act: -0.1700
Data Index: 8192190 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5793. Min Range: -6.5793
Max Act: 5.9856. Min Act: -0.1700
Data Index: 3115879 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5793. Min Range: -6.5793
Max Act: 5.9543. Min Act: -0.1700
Data Index: 1486118 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5793. Min Range: -6.5793
Max Act: 5.9543. Min Act: -0.1700
Data Index: 2532254 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5793. Min Range: -6.5793
Max Act: 5.9543. Min Act: -0.1700
Data Index: 5503419 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5793. Min Range: -6.5793
Max Act: 5.8918. Min Act: -0.1700
Data Index: 5792327 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5793. Min Range: -6.5793
Max Act: 5.8293. Min Act: -0.1700
Data Index: 1543388 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5793. Min Range: -6.5793
Max Act: 5.7981. Min Act: -0.1700
Data Index: 4307888 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5793. Min Range: -6.5793
Max Act: 5.8606. Min Act: -0.1700
Data Index: 1474054 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5793. Min Range: -6.5793
Max Act: 5.8293. Min Act: -0.1700
Data Index: 3080492 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5793. Min Range: -6.5793
Max Act: 5.7981. Min Act: -0.1700
Data Index: 1865129 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5793. Min Range: -6.5793
Max Act: 5.8293. Min Act: -0.1700
Data Index: 2877615 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5793. Min Range: -6.5793
Max Act: 5.8293. Min Act: -0.1700
Data Index: 419834 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19