Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2761 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.3426. Min Act: -0.1700
Data Index: 2886430 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.3426. Min Act: -0.1700
Data Index: 2179586 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.3112. Min Act: -0.1700
Data Index: 1014284 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.2641. Min Act: -0.1700
Data Index: 8024009 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.2170. Min Act: -0.1700
Data Index: 1284997 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.2013. Min Act: -0.1700
Data Index: 2724095 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.2327. Min Act: -0.1700
Data Index: 8417146 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.2170. Min Act: -0.1700
Data Index: 7974456 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.2327. Min Act: -0.1700
Data Index: 2900557 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.2170. Min Act: -0.1700
Data Index: 3455167 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.1855. Min Act: -0.1700
Data Index: 7594890 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.1855. Min Act: -0.1700
Data Index: 876011 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.1698. Min Act: -0.1700
Data Index: 1707740 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.1698. Min Act: -0.1700
Data Index: 275942 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.1698. Min Act: -0.1700
Data Index: 697534 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.1855. Min Act: -0.1700
Data Index: 4833201 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.1698. Min Act: -0.1700
Data Index: 7651301 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.1855. Min Act: -0.1700
Data Index: 1598136 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.1855. Min Act: -0.1700
Data Index: 179662 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3426. Min Range: -3.3426
Max Act: 3.1698. Min Act: -0.1700
Data Index: 651753 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19