Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2789 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4730. Min Range: -9.4730
Max Act: 9.4730. Min Act: -0.1700
Data Index: 6185148 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4730. Min Range: -9.4730
Max Act: 9.4730. Min Act: -0.1700
Data Index: 6463990 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4730. Min Range: -9.4730
Max Act: 9.2230. Min Act: -0.1700
Data Index: 3066778 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4730. Min Range: -9.4730
Max Act: 9.1605. Min Act: -0.1700
Data Index: 7637352 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4730. Min Range: -9.4730
Max Act: 9.0980. Min Act: -0.1700
Data Index: 7663736 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4730. Min Range: -9.4730
Max Act: 9.0355. Min Act: -0.1700
Data Index: 7237952 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4730. Min Range: -9.4730
Max Act: 8.9730. Min Act: -0.1700
Data Index: 5926539 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4730. Min Range: -9.4730
Max Act: 8.9730. Min Act: -0.1700
Data Index: 1499102 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4730. Min Range: -9.4730
Max Act: 8.9105. Min Act: -0.1700
Data Index: 5369958 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4730. Min Range: -9.4730
Max Act: 8.9105. Min Act: -0.1700
Data Index: 4821918 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4730. Min Range: -9.4730
Max Act: 8.9105. Min Act: -0.1700
Data Index: 5898246 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4730. Min Range: -9.4730
Max Act: 8.9105. Min Act: -0.1700
Data Index: 2860752 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4730. Min Range: -9.4730
Max Act: 8.8480. Min Act: -0.1700
Data Index: 581875 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4730. Min Range: -9.4730
Max Act: 8.8480. Min Act: -0.1700
Data Index: 1951165 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4730. Min Range: -9.4730
Max Act: 8.7855. Min Act: -0.1700
Data Index: 7827097 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4730. Min Range: -9.4730
Max Act: 8.7855. Min Act: -0.1700
Data Index: 880538 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4730. Min Range: -9.4730
Max Act: 8.7230. Min Act: -0.1700
Data Index: 808156 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4730. Min Range: -9.4730
Max Act: 8.7230. Min Act: -0.1700
Data Index: 3641081 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4730. Min Range: -9.4730
Max Act: 8.7230. Min Act: -0.1700
Data Index: 5333027 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4730. Min Range: -9.4730
Max Act: 8.6605. Min Act: -0.1700
Data Index: 7658843 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19