Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4852 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4616. Min Range: -7.4616
Max Act: 7.4616. Min Act: -0.1700
Data Index: 3898938 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4616. Min Range: -7.4616
Max Act: 7.3679. Min Act: -0.1700
Data Index: 53688 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4616. Min Range: -7.4616
Max Act: 7.1804. Min Act: -0.1700
Data Index: 787052 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4616. Min Range: -7.4616
Max Act: 7.1491. Min Act: -0.1700
Data Index: 1398306 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4616. Min Range: -7.4616
Max Act: 7.1491. Min Act: -0.1700
Data Index: 440593 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4616. Min Range: -7.4616
Max Act: 7.1179. Min Act: -0.1700
Data Index: 2838819 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4616. Min Range: -7.4616
Max Act: 7.0866. Min Act: -0.1700
Data Index: 8004711 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4616. Min Range: -7.4616
Max Act: 7.0554. Min Act: -0.1700
Data Index: 6844360 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4616. Min Range: -7.4616
Max Act: 7.0554. Min Act: -0.1700
Data Index: 3900143 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4616. Min Range: -7.4616
Max Act: 7.0554. Min Act: -0.1700
Data Index: 6526209 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4616. Min Range: -7.4616
Max Act: 7.0554. Min Act: -0.1700
Data Index: 1090922 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4616. Min Range: -7.4616
Max Act: 7.0241. Min Act: -0.1700
Data Index: 4742865 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4616. Min Range: -7.4616
Max Act: 6.9929. Min Act: -0.1700
Data Index: 4391919 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4616. Min Range: -7.4616
Max Act: 6.9616. Min Act: -0.1700
Data Index: 6472572 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4616. Min Range: -7.4616
Max Act: 6.9929. Min Act: -0.1700
Data Index: 1866419 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4616. Min Range: -7.4616
Max Act: 6.9616. Min Act: -0.1700
Data Index: 1864387 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4616. Min Range: -7.4616
Max Act: 6.9304. Min Act: -0.1700
Data Index: 3045601 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4616. Min Range: -7.4616
Max Act: 6.9304. Min Act: -0.1700
Data Index: 4993738 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4616. Min Range: -7.4616
Max Act: 6.9616. Min Act: -0.1700
Data Index: 3858835 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4616. Min Range: -7.4616
Max Act: 6.9616. Min Act: -0.1700
Data Index: 4628413 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19