Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3431 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7550. Min Range: -8.7550
Max Act: 8.7550. Min Act: -0.1700
Data Index: 4098329 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7550. Min Range: -8.7550
Max Act: 8.1925. Min Act: -0.1700
Data Index: 7444276 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7550. Min Range: -8.7550
Max Act: 8.0675. Min Act: -0.1700
Data Index: 941295 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7550. Min Range: -8.7550
Max Act: 7.8800. Min Act: -0.1700
Data Index: 6963770 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7550. Min Range: -8.7550
Max Act: 7.8175. Min Act: -0.1700
Data Index: 3838419 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7550. Min Range: -8.7550
Max Act: 7.7550. Min Act: -0.1700
Data Index: 5496474 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7550. Min Range: -8.7550
Max Act: 7.7550. Min Act: -0.1700
Data Index: 7476657 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7550. Min Range: -8.7550
Max Act: 7.7550. Min Act: -0.1700
Data Index: 3083198 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7550. Min Range: -8.7550
Max Act: 7.6925. Min Act: -0.1700
Data Index: 2824093 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7550. Min Range: -8.7550
Max Act: 7.7238. Min Act: -0.1700
Data Index: 4522095 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7550. Min Range: -8.7550
Max Act: 7.6925. Min Act: -0.1700
Data Index: 8216994 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7550. Min Range: -8.7550
Max Act: 7.6925. Min Act: -0.1700
Data Index: 6145629 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7550. Min Range: -8.7550
Max Act: 7.6925. Min Act: -0.1700
Data Index: 2630946 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7550. Min Range: -8.7550
Max Act: 7.6613. Min Act: -0.1700
Data Index: 1377526 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7550. Min Range: -8.7550
Max Act: 7.6613. Min Act: -0.1700
Data Index: 3245271 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7550. Min Range: -8.7550
Max Act: 7.6300. Min Act: -0.1700
Data Index: 6217174 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7550. Min Range: -8.7550
Max Act: 7.6300. Min Act: -0.1700
Data Index: 2490087 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7550. Min Range: -8.7550
Max Act: 7.6300. Min Act: -0.1700
Data Index: 7876145 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7550. Min Range: -8.7550
Max Act: 7.6300. Min Act: -0.1700
Data Index: 1206207 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7550. Min Range: -8.7550
Max Act: 7.5675. Min Act: -0.1700
Data Index: 2449949 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19