Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1915 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4861. Min Range: -5.4861
Max Act: 5.4861. Min Act: -0.1700
Data Index: 6379644 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4861. Min Range: -5.4861
Max Act: 5.4548. Min Act: -0.1700
Data Index: 3410532 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4861. Min Range: -5.4861
Max Act: 5.4548. Min Act: -0.1700
Data Index: 5025672 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4861. Min Range: -5.4861
Max Act: 5.4236. Min Act: -0.1700
Data Index: 8278521 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4861. Min Range: -5.4861
Max Act: 5.3923. Min Act: -0.1700
Data Index: 833458 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4861. Min Range: -5.4861
Max Act: 5.3298. Min Act: -0.1700
Data Index: 340985 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4861. Min Range: -5.4861
Max Act: 5.2361. Min Act: -0.1700
Data Index: 8818844 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4861. Min Range: -5.4861
Max Act: 5.1111. Min Act: -0.1700
Data Index: 1284508 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4861. Min Range: -5.4861
Max Act: 5.0798. Min Act: -0.1700
Data Index: 1921862 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4861. Min Range: -5.4861
Max Act: 4.9236. Min Act: -0.1700
Data Index: 8255601 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4861. Min Range: -5.4861
Max Act: 4.9236. Min Act: -0.1700
Data Index: 7198890 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4861. Min Range: -5.4861
Max Act: 4.9236. Min Act: -0.1700
Data Index: 5505239 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4861. Min Range: -5.4861
Max Act: 4.9236. Min Act: -0.1700
Data Index: 8374770 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4861. Min Range: -5.4861
Max Act: 4.9236. Min Act: -0.1700
Data Index: 6276685 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4861. Min Range: -5.4861
Max Act: 4.9236. Min Act: -0.1700
Data Index: 5826650 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4861. Min Range: -5.4861
Max Act: 4.8923. Min Act: -0.1700
Data Index: 7163840 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4861. Min Range: -5.4861
Max Act: 4.8611. Min Act: -0.1700
Data Index: 8371873 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4861. Min Range: -5.4861
Max Act: 4.8611. Min Act: -0.1700
Data Index: 7979171 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4861. Min Range: -5.4861
Max Act: 4.7986. Min Act: -0.1700
Data Index: 6875387 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4861. Min Range: -5.4861
Max Act: 4.7986. Min Act: -0.1700
Data Index: 279881 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19