Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5955. Min Range: -6.5955
Max Act: 6.5955. Min Act: -0.1700
Data Index: 3656920 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5955. Min Range: -6.5955
Max Act: 6.4393. Min Act: -0.1700
Data Index: 5514892 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5955. Min Range: -6.5955
Max Act: 6.1893. Min Act: -0.1700
Data Index: 4461538 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5955. Min Range: -6.5955
Max Act: 6.0955. Min Act: -0.1700
Data Index: 1708110 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5955. Min Range: -6.5955
Max Act: 6.0643. Min Act: -0.1700
Data Index: 5351478 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5955. Min Range: -6.5955
Max Act: 6.0643. Min Act: -0.1700
Data Index: 5878812 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5955. Min Range: -6.5955
Max Act: 6.0643. Min Act: -0.1700
Data Index: 827685 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5955. Min Range: -6.5955
Max Act: 6.0330. Min Act: -0.1700
Data Index: 724822 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5955. Min Range: -6.5955
Max Act: 6.0330. Min Act: -0.1700
Data Index: 1062595 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5955. Min Range: -6.5955
Max Act: 6.0018. Min Act: -0.1700
Data Index: 5556102 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5955. Min Range: -6.5955
Max Act: 5.9705. Min Act: -0.1700
Data Index: 641901 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5955. Min Range: -6.5955
Max Act: 5.9705. Min Act: -0.1700
Data Index: 78448 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5955. Min Range: -6.5955
Max Act: 5.9080. Min Act: -0.1700
Data Index: 5398867 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5955. Min Range: -6.5955
Max Act: 5.9080. Min Act: -0.1700
Data Index: 5373172 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5955. Min Range: -6.5955
Max Act: 5.9393. Min Act: -0.1700
Data Index: 6606942 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5955. Min Range: -6.5955
Max Act: 5.9393. Min Act: -0.1700
Data Index: 6533803 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5955. Min Range: -6.5955
Max Act: 5.9705. Min Act: -0.1700
Data Index: 6213360 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5955. Min Range: -6.5955
Max Act: 5.9393. Min Act: -0.1700
Data Index: 3836066 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5955. Min Range: -6.5955
Max Act: 5.9080. Min Act: -0.1700
Data Index: 67333 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5955. Min Range: -6.5955
Max Act: 5.9080. Min Act: -0.1700
Data Index: 4432287 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19