Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2137 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.7440. Min Act: -0.1700
Data Index: 8530845 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.7440. Min Act: -0.1700
Data Index: 8060944 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.7128. Min Act: -0.1700
Data Index: 7212484 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.6815. Min Act: -0.1700
Data Index: 2011211 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.6503. Min Act: -0.1700
Data Index: 5371726 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.5878. Min Act: -0.1700
Data Index: 8607038 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.5878. Min Act: -0.1700
Data Index: 2682838 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.5565. Min Act: -0.1700
Data Index: 150674 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.5565. Min Act: -0.1700
Data Index: 7369982 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.5565. Min Act: -0.1700
Data Index: 5299135 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.5253. Min Act: -0.1700
Data Index: 3297285 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.4940. Min Act: -0.1700
Data Index: 8317463 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.4940. Min Act: -0.1700
Data Index: 4250724 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.4940. Min Act: -0.1700
Data Index: 7689246 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.4628. Min Act: -0.1700
Data Index: 5406618 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.4628. Min Act: -0.1700
Data Index: 6154580 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.4628. Min Act: -0.1700
Data Index: 6573898 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.4315. Min Act: -0.1700
Data Index: 4482086 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.4315. Min Act: -0.1700
Data Index: 5011465 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7440. Min Range: -5.7440
Max Act: 5.4315. Min Act: -0.1700
Data Index: 3297284 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19