Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1651 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7095. Min Range: -8.7095
Max Act: 8.7095. Min Act: -0.1700
Data Index: 8648489 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7095. Min Range: -8.7095
Max Act: 8.2720. Min Act: -0.1700
Data Index: 1149161 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7095. Min Range: -8.7095
Max Act: 8.0845. Min Act: -0.1700
Data Index: 21981 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7095. Min Range: -8.7095
Max Act: 8.0533. Min Act: -0.1700
Data Index: 2698658 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7095. Min Range: -8.7095
Max Act: 8.0220. Min Act: -0.1700
Data Index: 8668343 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7095. Min Range: -8.7095
Max Act: 7.9908. Min Act: -0.1700
Data Index: 6937682 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7095. Min Range: -8.7095
Max Act: 7.9908. Min Act: -0.1700
Data Index: 6770037 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7095. Min Range: -8.7095
Max Act: 7.9908. Min Act: -0.1700
Data Index: 4125941 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7095. Min Range: -8.7095
Max Act: 7.9908. Min Act: -0.1700
Data Index: 3190184 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7095. Min Range: -8.7095
Max Act: 7.9283. Min Act: -0.1699
Data Index: 5672598 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7095. Min Range: -8.7095
Max Act: 7.9283. Min Act: -0.1700
Data Index: 219484 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7095. Min Range: -8.7095
Max Act: 7.8970. Min Act: -0.1700
Data Index: 5974158 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7095. Min Range: -8.7095
Max Act: 7.8658. Min Act: -0.1700
Data Index: 4699248 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7095. Min Range: -8.7095
Max Act: 7.8658. Min Act: -0.1700
Data Index: 1995271 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7095. Min Range: -8.7095
Max Act: 7.8345. Min Act: -0.1700
Data Index: 6699177 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7095. Min Range: -8.7095
Max Act: 7.7408. Min Act: -0.1700
Data Index: 6355942 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7095. Min Range: -8.7095
Max Act: 7.7095. Min Act: -0.1699
Data Index: 234930 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7095. Min Range: -8.7095
Max Act: 7.6783. Min Act: -0.1700
Data Index: 645920 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7095. Min Range: -8.7095
Max Act: 7.6783. Min Act: -0.1697
Data Index: 2275413 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7095. Min Range: -8.7095
Max Act: 7.6783. Min Act: -0.1700
Data Index: 7131896 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19