Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 845 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3094. Min Range: -5.3094
Max Act: 5.3094. Min Act: -0.1700
Data Index: 5607311 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3094. Min Range: -5.3094
Max Act: 5.2782. Min Act: -0.1700
Data Index: 6153247 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3094. Min Range: -5.3094
Max Act: 5.1844. Min Act: -0.1700
Data Index: 5449614 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3094. Min Range: -5.3094
Max Act: 5.1532. Min Act: -0.1700
Data Index: 1875057 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3094. Min Range: -5.3094
Max Act: 5.1219. Min Act: -0.1700
Data Index: 1416408 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3094. Min Range: -5.3094
Max Act: 5.0907. Min Act: -0.1700
Data Index: 7953562 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3094. Min Range: -5.3094
Max Act: 5.0282. Min Act: -0.1700
Data Index: 6382705 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3094. Min Range: -5.3094
Max Act: 4.9657. Min Act: -0.1700
Data Index: 6329560 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3094. Min Range: -5.3094
Max Act: 4.9344. Min Act: -0.1700
Data Index: 4709874 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3094. Min Range: -5.3094
Max Act: 4.9032. Min Act: -0.1700
Data Index: 3075162 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3094. Min Range: -5.3094
Max Act: 4.9344. Min Act: -0.1700
Data Index: 6688617 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3094. Min Range: -5.3094
Max Act: 4.9032. Min Act: -0.1700
Data Index: 2106936 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3094. Min Range: -5.3094
Max Act: 4.8407. Min Act: -0.1700
Data Index: 213369 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3094. Min Range: -5.3094
Max Act: 4.8407. Min Act: -0.1700
Data Index: 7521972 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3094. Min Range: -5.3094
Max Act: 4.8719. Min Act: -0.1700
Data Index: 1941330 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3094. Min Range: -5.3094
Max Act: 4.8719. Min Act: -0.1700
Data Index: 6423114 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3094. Min Range: -5.3094
Max Act: 4.8407. Min Act: -0.1700
Data Index: 7121671 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3094. Min Range: -5.3094
Max Act: 4.8407. Min Act: -0.1700
Data Index: 7185873 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3094. Min Range: -5.3094
Max Act: 4.8407. Min Act: -0.1700
Data Index: 1139191 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3094. Min Range: -5.3094
Max Act: 4.8094. Min Act: -0.1700
Data Index: 2092197 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19