Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1892 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0658. Min Range: -6.0658
Max Act: 6.0658. Min Act: -0.1700
Data Index: 5171619 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.9720. Min Act: -0.1700
Data Index: 2284087 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.8783. Min Act: -0.1700
Data Index: 2450735 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.8470. Min Act: -0.1700
Data Index: 6774260 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.8158. Min Act: -0.1700
Data Index: 5359520 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.8158. Min Act: -0.1700
Data Index: 8075623 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.8158. Min Act: -0.1700
Data Index: 4810878 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.8158. Min Act: -0.1700
Data Index: 5133377 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.7533. Min Act: -0.1700
Data Index: 688334 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.7533. Min Act: -0.1700
Data Index: 4025893 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.7533. Min Act: -0.1700
Data Index: 6774261 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.7220. Min Act: -0.1700
Data Index: 6774258 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.6908. Min Act: -0.1700
Data Index: 3841425 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.7220. Min Act: -0.1700
Data Index: 8745507 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.7220. Min Act: -0.1700
Data Index: 8581468 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.7220. Min Act: -0.1700
Data Index: 6662398 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.6908. Min Act: -0.1700
Data Index: 8356894 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.6908. Min Act: -0.1700
Data Index: 2362336 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.6908. Min Act: -0.1700
Data Index: 5737726 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0658. Min Range: -6.0658
Max Act: 5.6908. Min Act: -0.1700
Data Index: 968066 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19