Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4877 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.4990. Min Act: -0.1700
Data Index: 4651808 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.4111. Min Act: -0.1700
Data Index: 5130461 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.3934. Min Act: -0.1698
Data Index: 3113744 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.3405. Min Act: -0.1697
Data Index: 144759 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.3229. Min Act: -0.1700
Data Index: 7668533 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.3405. Min Act: -0.1700
Data Index: 1245170 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.3229. Min Act: -0.1700
Data Index: 8046525 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.3053. Min Act: -0.1700
Data Index: 2442457 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.3053. Min Act: -0.1668
Data Index: 6107999 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.2876. Min Act: -0.1699
Data Index: 1832684 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.3053. Min Act: -0.1699
Data Index: 5792385 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.2876. Min Act: -0.1699
Data Index: 6509287 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.2876. Min Act: -0.1686
Data Index: 7260583 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.2700. Min Act: -0.1698
Data Index: 8641980 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.2700. Min Act: -0.1700
Data Index: 1237587 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.2700. Min Act: -0.1693
Data Index: 3676099 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.2524. Min Act: -0.1680
Data Index: 5624177 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.2347. Min Act: -0.1700
Data Index: 3258314 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.2347. Min Act: -0.1691
Data Index: 1323150 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4990. Min Range: -1.4990
Max Act: 1.2171. Min Act: -0.1697
Data Index: 451819 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19