Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5957 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1776. Min Range: -7.1776
Max Act: 7.1776. Min Act: -0.1700
Data Index: 5271864 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1776. Min Range: -7.1776
Max Act: 7.0213. Min Act: -0.1700
Data Index: 1336521 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1776. Min Range: -7.1776
Max Act: 7.0213. Min Act: -0.1700
Data Index: 3415881 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.9901. Min Act: -0.1700
Data Index: 2610119 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.9588. Min Act: -0.1700
Data Index: 7257777 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.9276. Min Act: -0.1700
Data Index: 3103896 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.9276. Min Act: -0.1700
Data Index: 6336280 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.8963. Min Act: -0.1700
Data Index: 1067960 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.8651. Min Act: -0.1700
Data Index: 5040779 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.8651. Min Act: -0.1700
Data Index: 3551509 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.8651. Min Act: -0.1700
Data Index: 7923763 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.8338. Min Act: -0.1700
Data Index: 6009338 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.8338. Min Act: -0.1700
Data Index: 7012410 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.8026. Min Act: -0.1700
Data Index: 6066241 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.6776. Min Act: -0.1700
Data Index: 1628644 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.6463. Min Act: -0.1700
Data Index: 5363129 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.6151. Min Act: -0.1700
Data Index: 6858670 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.6151. Min Act: -0.1700
Data Index: 5618174 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.6151. Min Act: -0.1700
Data Index: 1905222 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.5526. Min Act: -0.1700
Data Index: 1336522 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19