Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 658 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.2799. Min Act: -0.1688
Data Index: 2215011 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.2301. Min Act: -0.1698
Data Index: 6496021 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.2181. Min Act: -0.1699
Data Index: 8565392 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.2063. Min Act: -0.1689
Data Index: 7913493 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.2122. Min Act: -0.1688
Data Index: 3627200 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.2063. Min Act: -0.1700
Data Index: 5775661 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.2122. Min Act: -0.1688
Data Index: 4334112 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.1946. Min Act: -0.1697
Data Index: 798698 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.1831. Min Act: -0.1700
Data Index: 6935018 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.1888. Min Act: -0.1697
Data Index: 2900264 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.1831. Min Act: -0.1691
Data Index: 714479 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.1888. Min Act: -0.1688
Data Index: 3498287 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.1888. Min Act: -0.1699
Data Index: 1861390 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.1774. Min Act: -0.1699
Data Index: 3889644 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.1831. Min Act: -0.1700
Data Index: 7559372 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.1831. Min Act: -0.1699
Data Index: 8626699 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.1888. Min Act: -0.1697
Data Index: 2192342 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.1831. Min Act: -0.1699
Data Index: 1691451 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.1831. Min Act: -0.1692
Data Index: 7869408 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2799. Min Range: -0.2799
Max Act: 0.1831. Min Act: -0.1700
Data Index: 4513527 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19