Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3755 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.3412. Min Act: -0.1700
Data Index: 1763332 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.3100. Min Act: -0.1700
Data Index: 1098353 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.2162. Min Act: -0.1700
Data Index: 1401318 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.2475. Min Act: -0.1700
Data Index: 2696847 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.2162. Min Act: -0.1700
Data Index: 7693816 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.1537. Min Act: -0.1700
Data Index: 50540 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.2162. Min Act: -0.1700
Data Index: 7741912 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.1850. Min Act: -0.1700
Data Index: 2829948 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.1225. Min Act: -0.1700
Data Index: 166474 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.1225. Min Act: -0.1700
Data Index: 2165709 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.0912. Min Act: -0.1700
Data Index: 7409293 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.0912. Min Act: -0.1700
Data Index: 3340238 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.0600. Min Act: -0.1700
Data Index: 1755945 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.0600. Min Act: -0.1700
Data Index: 3781292 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.0600. Min Act: -0.1700
Data Index: 3787903 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.0600. Min Act: -0.1700
Data Index: 6676670 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.0600. Min Act: -0.1700
Data Index: 8331127 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.0287. Min Act: -0.1700
Data Index: 416007 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3412. Min Range: -5.3412
Max Act: 5.0287. Min Act: -0.1700
Data Index: 5442847 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3412. Min Range: -5.3412
Max Act: 4.9975. Min Act: -0.1700
Data Index: 3067500 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19