Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3876 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.9142. Min Act: -0.1700
Data Index: 1681090 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.6955. Min Act: -0.1700
Data Index: 1393284 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.6642. Min Act: -0.1700
Data Index: 5585032 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.6017. Min Act: -0.1700
Data Index: 7784976 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.5392. Min Act: -0.1700
Data Index: 7478137 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.5392. Min Act: -0.1700
Data Index: 4668389 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.5080. Min Act: -0.1700
Data Index: 5067256 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.5080. Min Act: -0.1700
Data Index: 2608846 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.4767. Min Act: -0.1700
Data Index: 6298241 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.4767. Min Act: -0.1700
Data Index: 1247981 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.4142. Min Act: -0.1700
Data Index: 8678417 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.3830. Min Act: -0.1700
Data Index: 920693 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.3517. Min Act: -0.1700
Data Index: 7476963 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.3517. Min Act: -0.1700
Data Index: 1574187 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.2892. Min Act: -0.1700
Data Index: 8249796 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.2892. Min Act: -0.1700
Data Index: 1694409 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.2580. Min Act: -0.1700
Data Index: 1790252 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.2580. Min Act: -0.1700
Data Index: 2049742 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.2267. Min Act: -0.1700
Data Index: 6981998 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9142. Min Range: -6.9142
Max Act: 6.2267. Min Act: -0.1700
Data Index: 4752078 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19