Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1870 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1206. Min Range: -6.1206
Max Act: 6.1206. Min Act: -0.1700
Data Index: 5855732 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.9643. Min Act: -0.1700
Data Index: 3602439 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.9018. Min Act: -0.1700
Data Index: 1609639 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.8081. Min Act: -0.1700
Data Index: 5352900 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.8081. Min Act: -0.1700
Data Index: 1907365 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.7768. Min Act: -0.1700
Data Index: 2293771 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.7768. Min Act: -0.1700
Data Index: 6844866 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.7768. Min Act: -0.1700
Data Index: 7153129 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.7456. Min Act: -0.1700
Data Index: 2089508 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.7143. Min Act: -0.1700
Data Index: 425865 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.6831. Min Act: -0.1700
Data Index: 64546 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.6831. Min Act: -0.1700
Data Index: 7694544 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.6831. Min Act: -0.1700
Data Index: 2063117 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.6831. Min Act: -0.1700
Data Index: 2901608 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.6518. Min Act: -0.1700
Data Index: 703727 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.6206. Min Act: -0.1700
Data Index: 4014308 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.6206. Min Act: -0.1700
Data Index: 4522346 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.6206. Min Act: -0.1700
Data Index: 371327 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.6206. Min Act: -0.1700
Data Index: 8498101 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1206. Min Range: -6.1206
Max Act: 5.5893. Min Act: -0.1700
Data Index: 7951326 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19