Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3445 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.6508. Min Act: -0.1700
Data Index: 531429 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.6196. Min Act: -0.1700
Data Index: 1579664 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.5258. Min Act: -0.1700
Data Index: 1665432 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.4633. Min Act: -0.1700
Data Index: 7397380 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.4008. Min Act: -0.1700
Data Index: 8077311 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.4008. Min Act: -0.1700
Data Index: 828054 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.4008. Min Act: -0.1700
Data Index: 3472748 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.3696. Min Act: -0.1700
Data Index: 6540042 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.3696. Min Act: -0.1700
Data Index: 1460953 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.3696. Min Act: -0.1700
Data Index: 6300226 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.3383. Min Act: -0.1700
Data Index: 5639219 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.3383. Min Act: -0.1700
Data Index: 4065080 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.3383. Min Act: -0.1700
Data Index: 3648918 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.3383. Min Act: -0.1700
Data Index: 376920 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.3696. Min Act: -0.1700
Data Index: 236076 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.3071. Min Act: -0.1700
Data Index: 3648921 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.2758. Min Act: -0.1700
Data Index: 426172 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.2758. Min Act: -0.1700
Data Index: 1023064 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.2446. Min Act: -0.1700
Data Index: 6144727 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6508. Min Range: -6.6508
Max Act: 6.2446. Min Act: -0.1700
Data Index: 6144726 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19