Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2837 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.6830. Min Act: -0.1700
Data Index: 6976131 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.6517. Min Act: -0.1700
Data Index: 6734591 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.6205. Min Act: -0.1700
Data Index: 4596030 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.5267. Min Act: -0.1700
Data Index: 8106619 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4955. Min Act: -0.1699
Data Index: 5653877 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4642. Min Act: -0.1700
Data Index: 2250218 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4642. Min Act: -0.1700
Data Index: 3610037 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4642. Min Act: -0.1700
Data Index: 5693501 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4642. Min Act: -0.1700
Data Index: 826121 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4642. Min Act: -0.1700
Data Index: 8139277 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4330. Min Act: -0.1700
Data Index: 1357416 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4330. Min Act: -0.1700
Data Index: 1056165 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4017. Min Act: -0.1700
Data Index: 3510102 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4017. Min Act: -0.1700
Data Index: 7931719 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4017. Min Act: -0.1700
Data Index: 6175775 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3705. Min Act: -0.1700
Data Index: 3335170 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3392. Min Act: -0.1700
Data Index: 5755047 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3705. Min Act: -0.1700
Data Index: 4825234 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4017. Min Act: -0.1700
Data Index: 2794919 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3705. Min Act: -0.1700
Data Index: 1121989 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19