Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2072 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4740. Min Range: -6.4740
Max Act: 6.4740. Min Act: -0.1700
Data Index: 2312839 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4740. Min Range: -6.4740
Max Act: 6.1302. Min Act: -0.1700
Data Index: 1816777 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4740. Min Range: -6.4740
Max Act: 5.9740. Min Act: -0.1700
Data Index: 2536519 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4740. Min Range: -6.4740
Max Act: 5.9427. Min Act: -0.1700
Data Index: 6744691 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4740. Min Range: -6.4740
Max Act: 5.9427. Min Act: -0.1700
Data Index: 571734 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4740. Min Range: -6.4740
Max Act: 5.9115. Min Act: -0.1700
Data Index: 1638370 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4740. Min Range: -6.4740
Max Act: 5.8802. Min Act: -0.1700
Data Index: 830505 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4740. Min Range: -6.4740
Max Act: 5.8490. Min Act: -0.1700
Data Index: 3117823 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4740. Min Range: -6.4740
Max Act: 5.8490. Min Act: -0.1700
Data Index: 6075277 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4740. Min Range: -6.4740
Max Act: 5.8490. Min Act: -0.1700
Data Index: 3099923 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4740. Min Range: -6.4740
Max Act: 5.8490. Min Act: -0.1700
Data Index: 3329608 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4740. Min Range: -6.4740
Max Act: 5.8177. Min Act: -0.1700
Data Index: 3448960 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4740. Min Range: -6.4740
Max Act: 5.8177. Min Act: -0.1700
Data Index: 917645 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4740. Min Range: -6.4740
Max Act: 5.7865. Min Act: -0.1700
Data Index: 4036391 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4740. Min Range: -6.4740
Max Act: 5.7552. Min Act: -0.1700
Data Index: 7625958 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4740. Min Range: -6.4740
Max Act: 5.7552. Min Act: -0.1700
Data Index: 7095906 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4740. Min Range: -6.4740
Max Act: 5.7552. Min Act: -0.1700
Data Index: 3790410 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4740. Min Range: -6.4740
Max Act: 5.7240. Min Act: -0.1700
Data Index: 6059293 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4740. Min Range: -6.4740
Max Act: 5.7240. Min Act: -0.1700
Data Index: 4030547 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4740. Min Range: -6.4740
Max Act: 5.6927. Min Act: -0.1700
Data Index: 5995722 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19