Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5656 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8275. Min Range: -7.8275
Max Act: 7.8275. Min Act: -0.1700
Data Index: 7106663 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8275. Min Range: -7.8275
Max Act: 7.2338. Min Act: -0.1700
Data Index: 8626520 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8275. Min Range: -7.8275
Max Act: 7.2025. Min Act: -0.1700
Data Index: 7361966 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8275. Min Range: -7.8275
Max Act: 6.9838. Min Act: -0.1700
Data Index: 4984001 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8275. Min Range: -7.8275
Max Act: 6.9213. Min Act: -0.1700
Data Index: 6592872 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8275. Min Range: -7.8275
Max Act: 6.8588. Min Act: -0.1700
Data Index: 6058197 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8275. Min Range: -7.8275
Max Act: 6.8588. Min Act: -0.1700
Data Index: 6784468 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8275. Min Range: -7.8275
Max Act: 6.8275. Min Act: -0.1700
Data Index: 8295257 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8275. Min Range: -7.8275
Max Act: 6.7963. Min Act: -0.1700
Data Index: 4816399 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8275. Min Range: -7.8275
Max Act: 6.7963. Min Act: -0.1700
Data Index: 4787745 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8275. Min Range: -7.8275
Max Act: 6.7650. Min Act: -0.1700
Data Index: 2484745 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8275. Min Range: -7.8275
Max Act: 6.7963. Min Act: -0.1700
Data Index: 8211701 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8275. Min Range: -7.8275
Max Act: 6.7338. Min Act: -0.1700
Data Index: 4536135 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8275. Min Range: -7.8275
Max Act: 6.7025. Min Act: -0.1700
Data Index: 2089395 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8275. Min Range: -7.8275
Max Act: 6.7025. Min Act: -0.1700
Data Index: 8105300 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8275. Min Range: -7.8275
Max Act: 6.6713. Min Act: -0.1700
Data Index: 1301555 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8275. Min Range: -7.8275
Max Act: 6.6713. Min Act: -0.1700
Data Index: 1671702 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8275. Min Range: -7.8275
Max Act: 6.6713. Min Act: -0.1700
Data Index: 668690 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8275. Min Range: -7.8275
Max Act: 6.6088. Min Act: -0.1700
Data Index: 356098 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8275. Min Range: -7.8275
Max Act: 6.6400. Min Act: -0.1700
Data Index: 8624005 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19