Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 727 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.7343. Min Act: -0.1700
Data Index: 5806297 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.6405. Min Act: -0.1700
Data Index: 4288608 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.3280. Min Act: -0.1700
Data Index: 2401990 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.2343. Min Act: -0.1700
Data Index: 5319074 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.1718. Min Act: -0.1700
Data Index: 1271627 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.1718. Min Act: -0.1700
Data Index: 7702741 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.1405. Min Act: -0.1700
Data Index: 815565 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.1405. Min Act: -0.1700
Data Index: 3706440 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.1093. Min Act: -0.1700
Data Index: 237700 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.1093. Min Act: -0.1700
Data Index: 510319 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.1093. Min Act: -0.1700
Data Index: 1411045 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.1093. Min Act: -0.1700
Data Index: 600730 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.1093. Min Act: -0.1700
Data Index: 5040531 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.0780. Min Act: -0.1700
Data Index: 6637871 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.0780. Min Act: -0.1700
Data Index: 5826240 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.0780. Min Act: -0.1700
Data Index: 6343411 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.0467. Min Act: -0.1700
Data Index: 1219412 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.0467. Min Act: -0.1700
Data Index: 6138057 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.0467. Min Act: -0.1700
Data Index: 1266878 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7343. Min Range: -4.7343
Max Act: 4.0155. Min Act: -0.1700
Data Index: 2137108 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19