Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3308 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.4658. Min Act: -0.1700
Data Index: 7713073 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.4170. Min Act: -0.1700
Data Index: 5796153 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.4170. Min Act: -0.1700
Data Index: 6950968 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.4170. Min Act: -0.1700
Data Index: 3104655 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.4170. Min Act: -0.1700
Data Index: 1468983 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.4170. Min Act: -0.1700
Data Index: 6098521 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.3844. Min Act: -0.1700
Data Index: 8257072 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.4007. Min Act: -0.1700
Data Index: 1769138 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.3844. Min Act: -0.1700
Data Index: 6334631 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.3680. Min Act: -0.1700
Data Index: 715580 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.3844. Min Act: -0.1700
Data Index: 6339868 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.3517. Min Act: -0.1700
Data Index: 7604862 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.3517. Min Act: -0.1700
Data Index: 7614346 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.3517. Min Act: -0.1700
Data Index: 940099 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.3517. Min Act: -0.1700
Data Index: 8300908 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.3353. Min Act: -0.1700
Data Index: 520703 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.3189. Min Act: -0.1700
Data Index: 728845 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.3353. Min Act: -0.1700
Data Index: 2982725 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.3353. Min Act: -0.1700
Data Index: 944340 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4658. Min Range: -2.4658
Max Act: 2.3353. Min Act: -0.1700
Data Index: 6173205 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19