Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1818 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.7494. Min Act: -0.1700
Data Index: 3394372 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.0276. Min Act: -0.1700
Data Index: 2802817 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.0118. Min Act: -0.1700
Data Index: 4998266 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7494. Min Range: -3.7494
Max Act: 2.9960. Min Act: -0.1700
Data Index: 2157899 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7494. Min Range: -3.7494
Max Act: 2.9960. Min Act: -0.1700
Data Index: 2721093 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7494. Min Range: -3.7494
Max Act: 2.9801. Min Act: -0.1700
Data Index: 5714456 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7494. Min Range: -3.7494
Max Act: 2.9801. Min Act: -0.1700
Data Index: 2098036 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7494. Min Range: -3.7494
Max Act: 2.9643. Min Act: -0.1700
Data Index: 4924330 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7494. Min Range: -3.7494
Max Act: 2.9960. Min Act: -0.1700
Data Index: 1163160 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7494. Min Range: -3.7494
Max Act: 2.9643. Min Act: -0.1700
Data Index: 6169756 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7494. Min Range: -3.7494
Max Act: 2.9168. Min Act: -0.1700
Data Index: 896189 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7494. Min Range: -3.7494
Max Act: 2.9168. Min Act: -0.1700
Data Index: 6637181 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7494. Min Range: -3.7494
Max Act: 2.9327. Min Act: -0.1700
Data Index: 6944007 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7494. Min Range: -3.7494
Max Act: 2.9010. Min Act: -0.1700
Data Index: 5280424 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7494. Min Range: -3.7494
Max Act: 2.9485. Min Act: -0.1700
Data Index: 5929162 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7494. Min Range: -3.7494
Max Act: 2.9010. Min Act: -0.1700
Data Index: 3260205 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7494. Min Range: -3.7494
Max Act: 2.8692. Min Act: -0.1700
Data Index: 1453619 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7494. Min Range: -3.7494
Max Act: 2.8692. Min Act: -0.1700
Data Index: 3692455 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7494. Min Range: -3.7494
Max Act: 2.8851. Min Act: -0.1700
Data Index: 6475936 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7494. Min Range: -3.7494
Max Act: 2.8692. Min Act: -0.1700
Data Index: 3632633 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19