Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4107 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6307. Min Range: -5.6307
Max Act: 5.6307. Min Act: -0.1700
Data Index: 6984415 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6307. Min Range: -5.6307
Max Act: 5.3494. Min Act: -0.1700
Data Index: 4181674 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6307. Min Range: -5.6307
Max Act: 5.3182. Min Act: -0.1700
Data Index: 380495 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6307. Min Range: -5.6307
Max Act: 5.2244. Min Act: -0.1700
Data Index: 6522205 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6307. Min Range: -5.6307
Max Act: 5.1932. Min Act: -0.1700
Data Index: 7030796 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6307. Min Range: -5.6307
Max Act: 5.1932. Min Act: -0.1700
Data Index: 7747962 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6307. Min Range: -5.6307
Max Act: 5.1307. Min Act: -0.1700
Data Index: 7155063 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6307. Min Range: -5.6307
Max Act: 5.1307. Min Act: -0.1700
Data Index: 7464739 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6307. Min Range: -5.6307
Max Act: 5.0994. Min Act: -0.1700
Data Index: 4316863 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6307. Min Range: -5.6307
Max Act: 5.0682. Min Act: -0.1700
Data Index: 6279505 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6307. Min Range: -5.6307
Max Act: 5.0682. Min Act: -0.1700
Data Index: 4336549 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6307. Min Range: -5.6307
Max Act: 5.0682. Min Act: -0.1700
Data Index: 3648071 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6307. Min Range: -5.6307
Max Act: 5.0369. Min Act: -0.1700
Data Index: 1625293 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6307. Min Range: -5.6307
Max Act: 5.0369. Min Act: -0.1700
Data Index: 1503437 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6307. Min Range: -5.6307
Max Act: 5.0369. Min Act: -0.1700
Data Index: 4542081 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6307. Min Range: -5.6307
Max Act: 5.0057. Min Act: -0.1700
Data Index: 5719497 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6307. Min Range: -5.6307
Max Act: 5.0369. Min Act: -0.1700
Data Index: 680012 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6307. Min Range: -5.6307
Max Act: 4.9744. Min Act: -0.1700
Data Index: 3517167 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6307. Min Range: -5.6307
Max Act: 4.9744. Min Act: -0.1700
Data Index: 4391851 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6307. Min Range: -5.6307
Max Act: 4.9744. Min Act: -0.1700
Data Index: 4273341 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19