Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3528 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.5381. Min Act: -0.1700
Data Index: 281770 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.4131. Min Act: -0.1700
Data Index: 331107 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.3819. Min Act: -0.1700
Data Index: 3281041 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.3194. Min Act: -0.1700
Data Index: 7115623 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.3194. Min Act: -0.1700
Data Index: 7492683 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.3194. Min Act: -0.1700
Data Index: 3817462 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.2881. Min Act: -0.1700
Data Index: 6297104 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.2881. Min Act: -0.1700
Data Index: 3949671 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.2569. Min Act: -0.1700
Data Index: 1046131 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.2256. Min Act: -0.1700
Data Index: 655877 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.2256. Min Act: -0.1700
Data Index: 5587315 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.1944. Min Act: -0.1700
Data Index: 6785338 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.1631. Min Act: -0.1700
Data Index: 509060 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.1631. Min Act: -0.1700
Data Index: 8080231 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.1631. Min Act: -0.1700
Data Index: 2152511 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.1319. Min Act: -0.1700
Data Index: 615739 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.1631. Min Act: -0.1700
Data Index: 3136917 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.1631. Min Act: -0.1700
Data Index: 2707952 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.1319. Min Act: -0.1700
Data Index: 2142701 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5381. Min Range: -5.5381
Max Act: 5.1631. Min Act: -0.1700
Data Index: 8002990 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19