Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5334 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3794. Min Range: -5.3794
Max Act: 5.3794. Min Act: -0.1700
Data Index: 2817474 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3794. Min Range: -5.3794
Max Act: 5.3481. Min Act: -0.1700
Data Index: 4865531 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3794. Min Range: -5.3794
Max Act: 5.2856. Min Act: -0.1700
Data Index: 927552 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3794. Min Range: -5.3794
Max Act: 5.1606. Min Act: -0.1700
Data Index: 8623874 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3794. Min Range: -5.3794
Max Act: 5.1606. Min Act: -0.1700
Data Index: 4143040 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3794. Min Range: -5.3794
Max Act: 5.1294. Min Act: -0.1700
Data Index: 7335321 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3794. Min Range: -5.3794
Max Act: 5.1294. Min Act: -0.1700
Data Index: 8391594 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3794. Min Range: -5.3794
Max Act: 5.0981. Min Act: -0.1700
Data Index: 6269772 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3794. Min Range: -5.3794
Max Act: 5.0981. Min Act: -0.1700
Data Index: 296243 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3794. Min Range: -5.3794
Max Act: 5.0669. Min Act: -0.1700
Data Index: 2501708 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3794. Min Range: -5.3794
Max Act: 5.0356. Min Act: -0.1700
Data Index: 168250 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3794. Min Range: -5.3794
Max Act: 4.9731. Min Act: -0.1700
Data Index: 47227 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3794. Min Range: -5.3794
Max Act: 4.9731. Min Act: -0.1700
Data Index: 2279126 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3794. Min Range: -5.3794
Max Act: 4.9731. Min Act: -0.1700
Data Index: 2157916 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3794. Min Range: -5.3794
Max Act: 4.9731. Min Act: -0.1700
Data Index: 2241343 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3794. Min Range: -5.3794
Max Act: 4.9419. Min Act: -0.1700
Data Index: 5876939 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3794. Min Range: -5.3794
Max Act: 4.8794. Min Act: -0.1700
Data Index: 8159222 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3794. Min Range: -5.3794
Max Act: 4.9106. Min Act: -0.1700
Data Index: 5251249 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3794. Min Range: -5.3794
Max Act: 4.9106. Min Act: -0.1700
Data Index: 2508762 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3794. Min Range: -5.3794
Max Act: 4.9106. Min Act: -0.1700
Data Index: 7451901 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19