Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2100 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0564. Min Range: -2.0564
Max Act: 2.0564. Min Act: -0.1650
Data Index: 1442677 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0564. Min Range: -2.0564
Max Act: 2.0227. Min Act: -0.1686
Data Index: 4155667 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0564. Min Range: -2.0564
Max Act: 1.9466. Min Act: -0.1700
Data Index: 4689923 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0564. Min Range: -2.0564
Max Act: 1.9466. Min Act: -0.1699
Data Index: 1960438 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0564. Min Range: -2.0564
Max Act: 1.9550. Min Act: -0.1690
Data Index: 3876689 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0564. Min Range: -2.0564
Max Act: 1.9550. Min Act: -0.1663
Data Index: 5665195 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0564. Min Range: -2.0564
Max Act: 1.9296. Min Act: -0.1700
Data Index: 3876688 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0564. Min Range: -2.0564
Max Act: 1.9125. Min Act: -0.1700
Data Index: 5024439 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0564. Min Range: -2.0564
Max Act: 1.8955. Min Act: -0.1700
Data Index: 7123744 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0564. Min Range: -2.0564
Max Act: 1.9040. Min Act: -0.1700
Data Index: 7191843 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0564. Min Range: -2.0564
Max Act: 1.8613. Min Act: -0.1700
Data Index: 7423305 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0564. Min Range: -2.0564
Max Act: 1.8613. Min Act: -0.1700
Data Index: 7123759 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0564. Min Range: -2.0564
Max Act: 1.8013. Min Act: -0.1698
Data Index: 5112898 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0564. Min Range: -2.0564
Max Act: 1.8185. Min Act: -0.1699
Data Index: 361618 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0564. Min Range: -2.0564
Max Act: 1.7927. Min Act: -0.1695
Data Index: 8058636 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0564. Min Range: -2.0564
Max Act: 1.8013. Min Act: -0.1699
Data Index: 3406188 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0564. Min Range: -2.0564
Max Act: 1.7927. Min Act: -0.1698
Data Index: 2449821 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0564. Min Range: -2.0564
Max Act: 1.7927. Min Act: -0.1690
Data Index: 6358163 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0564. Min Range: -2.0564
Max Act: 1.7668. Min Act: -0.1697
Data Index: 3876687 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0564. Min Range: -2.0564
Max Act: 1.7927. Min Act: -0.1697
Data Index: 7104924 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19