Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1872 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.5571. Min Act: -0.1700
Data Index: 5637245 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.4633. Min Act: -0.1700
Data Index: 3356841 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.4321. Min Act: -0.1700
Data Index: 8202588 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.3696. Min Act: -0.1700
Data Index: 172176 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.3696. Min Act: -0.1700
Data Index: 3122312 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.3696. Min Act: -0.1700
Data Index: 5540516 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.3696. Min Act: -0.1700
Data Index: 5867836 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.3071. Min Act: -0.1700
Data Index: 5158436 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.3071. Min Act: -0.1700
Data Index: 5330999 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.2758. Min Act: -0.1700
Data Index: 6180753 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.2758. Min Act: -0.1700
Data Index: 377438 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.2446. Min Act: -0.1700
Data Index: 5928950 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.2446. Min Act: -0.1700
Data Index: 8628133 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.2446. Min Act: -0.1700
Data Index: 393253 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.2133. Min Act: -0.1700
Data Index: 4539346 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.1821. Min Act: -0.1700
Data Index: 3583262 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.1821. Min Act: -0.1700
Data Index: 8771412 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.1508. Min Act: -0.1700
Data Index: 4757830 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.1508. Min Act: -0.1700
Data Index: 5834105 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5571. Min Range: -5.5571
Max Act: 5.1508. Min Act: -0.1700
Data Index: 595367 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19