Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3638 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0287. Min Range: -6.0287
Max Act: 6.0287. Min Act: -0.1700
Data Index: 3051959 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.9662. Min Act: -0.1700
Data Index: 6781421 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.8725. Min Act: -0.1700
Data Index: 8780720 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.8725. Min Act: -0.1700
Data Index: 8492785 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.8412. Min Act: -0.1700
Data Index: 4064241 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.8100. Min Act: -0.1700
Data Index: 6771591 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.7787. Min Act: -0.1700
Data Index: 2603122 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.7475. Min Act: -0.1700
Data Index: 4895669 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.7162. Min Act: -0.1700
Data Index: 1048110 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.7162. Min Act: -0.1700
Data Index: 3641621 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.7162. Min Act: -0.1700
Data Index: 7460004 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.7162. Min Act: -0.1700
Data Index: 3584952 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.7162. Min Act: -0.1700
Data Index: 4621267 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.7162. Min Act: -0.1700
Data Index: 7450960 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.7475. Min Act: -0.1700
Data Index: 5131795 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.6850. Min Act: -0.1700
Data Index: 7227197 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.6850. Min Act: -0.1700
Data Index: 4607861 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.6850. Min Act: -0.1700
Data Index: 2824989 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.6850. Min Act: -0.1700
Data Index: 2338714 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0287. Min Range: -6.0287
Max Act: 5.6850. Min Act: -0.1700
Data Index: 6216340 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19