Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5403 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.8809. Min Act: -0.1700
Data Index: 114010 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.8497. Min Act: -0.1700
Data Index: 7681031 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.8184. Min Act: -0.1700
Data Index: 4890256 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.8184. Min Act: -0.1700
Data Index: 2344754 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.7872. Min Act: -0.1700
Data Index: 3859276 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.7872. Min Act: -0.1700
Data Index: 4148890 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.7872. Min Act: -0.1700
Data Index: 4818836 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.7872. Min Act: -0.1700
Data Index: 1901453 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.7559. Min Act: -0.1700
Data Index: 7030042 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.7559. Min Act: -0.1700
Data Index: 6238655 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.7247. Min Act: -0.1700
Data Index: 4130292 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.7247. Min Act: -0.1700
Data Index: 8025392 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.6934. Min Act: -0.1700
Data Index: 6751591 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.6934. Min Act: -0.1700
Data Index: 1444448 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.6934. Min Act: -0.1700
Data Index: 5716482 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.6934. Min Act: -0.1700
Data Index: 1301911 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.6934. Min Act: -0.1700
Data Index: 6353918 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.6934. Min Act: -0.1700
Data Index: 7498 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.6934. Min Act: -0.1700
Data Index: 7106869 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8809. Min Range: -4.8809
Max Act: 4.6622. Min Act: -0.1700
Data Index: 5590200 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19