Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2234 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0271. Min Range: -9.0271
Max Act: 9.0271. Min Act: -0.1700
Data Index: 1136966 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.7771. Min Act: -0.1700
Data Index: 1240031 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.6521. Min Act: -0.1700
Data Index: 4946642 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.5896. Min Act: -0.1700
Data Index: 5722769 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.5271. Min Act: -0.1700
Data Index: 1943249 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.3396. Min Act: -0.1700
Data Index: 6554546 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.4021. Min Act: -0.1700
Data Index: 7189473 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.4021. Min Act: -0.1700
Data Index: 289442 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.3396. Min Act: -0.1700
Data Index: 8187824 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.2771. Min Act: -0.1700
Data Index: 8329075 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.2771. Min Act: -0.1700
Data Index: 1309819 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.2146. Min Act: -0.1700
Data Index: 4697380 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.1521. Min Act: -0.1700
Data Index: 5911670 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.1521. Min Act: -0.1700
Data Index: 1179000 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.1521. Min Act: -0.1700
Data Index: 4266738 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.1209. Min Act: -0.1700
Data Index: 6935189 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.0896. Min Act: -0.1700
Data Index: 3751395 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.0896. Min Act: -0.1700
Data Index: 6099244 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.0584. Min Act: -0.1700
Data Index: 491059 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0271. Min Range: -9.0271
Max Act: 8.0271. Min Act: -0.1700
Data Index: 6600058 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19