Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1759 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.7044. Min Act: -0.1700
Data Index: 445260 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.7044. Min Act: -0.1700
Data Index: 7255208 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.6419. Min Act: -0.1700
Data Index: 6204485 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.6106. Min Act: -0.1700
Data Index: 6480842 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.5794. Min Act: -0.1700
Data Index: 8414007 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.5794. Min Act: -0.1700
Data Index: 3188601 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.5169. Min Act: -0.1700
Data Index: 3080367 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.5481. Min Act: -0.1700
Data Index: 3171243 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.5169. Min Act: -0.1700
Data Index: 1551396 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.5169. Min Act: -0.1700
Data Index: 706988 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.5169. Min Act: -0.1700
Data Index: 2362513 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.4544. Min Act: -0.1700
Data Index: 5229187 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.4856. Min Act: -0.1700
Data Index: 1446901 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.4856. Min Act: -0.1700
Data Index: 5555432 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.4856. Min Act: -0.1700
Data Index: 1485403 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.4856. Min Act: -0.1700
Data Index: 2857724 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.4856. Min Act: -0.1700
Data Index: 3713058 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.4544. Min Act: -0.1700
Data Index: 2580414 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.4544. Min Act: -0.1700
Data Index: 6352237 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7044. Min Range: -5.7044
Max Act: 5.4544. Min Act: -0.1700
Data Index: 4214476 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19