Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5046 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.3910. Min Act: -0.1700
Data Index: 2272029 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.3910. Min Act: -0.1700
Data Index: 7014134 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.3597. Min Act: -0.1700
Data Index: 7710021 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.3597. Min Act: -0.1700
Data Index: 1666238 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.3597. Min Act: -0.1700
Data Index: 8513880 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.3285. Min Act: -0.1700
Data Index: 2105429 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.3285. Min Act: -0.1700
Data Index: 7510844 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.2972. Min Act: -0.1700
Data Index: 7476570 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.2347. Min Act: -0.1700
Data Index: 2064643 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.2660. Min Act: -0.1700
Data Index: 5677180 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.2035. Min Act: -0.1700
Data Index: 8188149 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.2347. Min Act: -0.1700
Data Index: 519364 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.2035. Min Act: -0.1700
Data Index: 8514986 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.2347. Min Act: -0.1700
Data Index: 5705649 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.2347. Min Act: -0.1700
Data Index: 7255877 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.2035. Min Act: -0.1700
Data Index: 1247197 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.1722. Min Act: -0.1700
Data Index: 1139567 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.1410. Min Act: -0.1700
Data Index: 8639933 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.1410. Min Act: -0.1700
Data Index: 6217647 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3910. Min Range: -6.3910
Max Act: 6.1097. Min Act: -0.1700
Data Index: 129646 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19