Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 101 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.4835. Min Act: -0.1700
Data Index: 6347370 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.4210. Min Act: -0.1700
Data Index: 1304128 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.3897. Min Act: -0.1700
Data Index: 3008888 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.2960. Min Act: -0.1700
Data Index: 5429079 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.2647. Min Act: -0.1700
Data Index: 855489 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.2960. Min Act: -0.1700
Data Index: 1775813 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.2647. Min Act: -0.1700
Data Index: 3996114 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.2647. Min Act: -0.1700
Data Index: 3530040 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.2022. Min Act: -0.1700
Data Index: 2622250 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.2335. Min Act: -0.1700
Data Index: 3025927 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.2022. Min Act: -0.1700
Data Index: 3379935 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.1710. Min Act: -0.1700
Data Index: 7248189 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.1710. Min Act: -0.1700
Data Index: 2344247 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.1710. Min Act: -0.1700
Data Index: 7742371 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.1710. Min Act: -0.1700
Data Index: 1223137 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.1397. Min Act: -0.1700
Data Index: 3793401 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.1397. Min Act: -0.1700
Data Index: 4468089 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.1397. Min Act: -0.1700
Data Index: 4545178 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.1085. Min Act: -0.1700
Data Index: 3867992 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4835. Min Range: -5.4835
Max Act: 5.1397. Min Act: -0.1700
Data Index: 2860514 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19