Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1705 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7162. Min Range: -6.7162
Max Act: 6.7162. Min Act: -0.1700
Data Index: 7995792 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7162. Min Range: -6.7162
Max Act: 6.2787. Min Act: -0.1700
Data Index: 8409099 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7162. Min Range: -6.7162
Max Act: 6.2474. Min Act: -0.1700
Data Index: 6959735 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7162. Min Range: -6.7162
Max Act: 6.0599. Min Act: -0.1700
Data Index: 4554395 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7162. Min Range: -6.7162
Max Act: 6.0912. Min Act: -0.1700
Data Index: 5006926 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7162. Min Range: -6.7162
Max Act: 6.0287. Min Act: -0.1700
Data Index: 575607 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7162. Min Range: -6.7162
Max Act: 5.9974. Min Act: -0.1700
Data Index: 2687619 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7162. Min Range: -6.7162
Max Act: 6.0287. Min Act: -0.1700
Data Index: 5587220 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7162. Min Range: -6.7162
Max Act: 5.9662. Min Act: -0.1700
Data Index: 3402269 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7162. Min Range: -6.7162
Max Act: 5.9974. Min Act: -0.1700
Data Index: 7520203 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7162. Min Range: -6.7162
Max Act: 5.9349. Min Act: -0.1700
Data Index: 3216248 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7162. Min Range: -6.7162
Max Act: 5.9662. Min Act: -0.1700
Data Index: 1029212 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7162. Min Range: -6.7162
Max Act: 5.9349. Min Act: -0.1700
Data Index: 57794 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7162. Min Range: -6.7162
Max Act: 5.9349. Min Act: -0.1700
Data Index: 2709220 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7162. Min Range: -6.7162
Max Act: 5.9037. Min Act: -0.1700
Data Index: 3316255 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7162. Min Range: -6.7162
Max Act: 5.9349. Min Act: -0.1700
Data Index: 1210683 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7162. Min Range: -6.7162
Max Act: 5.9037. Min Act: -0.1700
Data Index: 4996726 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7162. Min Range: -6.7162
Max Act: 5.8724. Min Act: -0.1700
Data Index: 805662 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7162. Min Range: -6.7162
Max Act: 5.9037. Min Act: -0.1700
Data Index: 8280778 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7162. Min Range: -6.7162
Max Act: 5.9037. Min Act: -0.1700
Data Index: 4990122 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19