Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3029 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.1177. Min Range: -9.1177
Max Act: 9.1177. Min Act: -0.1700
Data Index: 2542908 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.9927. Min Act: -0.1700
Data Index: 190581 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.9302. Min Act: -0.1700
Data Index: 5316531 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.8677. Min Act: -0.1700
Data Index: 7452505 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.8677. Min Act: -0.1700
Data Index: 5707173 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.8052. Min Act: -0.1700
Data Index: 353325 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.8052. Min Act: -0.1700
Data Index: 6098516 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.8052. Min Act: -0.1700
Data Index: 6939779 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.7427. Min Act: -0.1700
Data Index: 6710786 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.7427. Min Act: -0.1700
Data Index: 6893326 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.6802. Min Act: -0.1700
Data Index: 5809814 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.6802. Min Act: -0.1700
Data Index: 1520105 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.6802. Min Act: -0.1700
Data Index: 6008428 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.6802. Min Act: -0.1700
Data Index: 2292586 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.6802. Min Act: -0.1700
Data Index: 7428009 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.6177. Min Act: -0.1700
Data Index: 4022175 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.5552. Min Act: -0.1700
Data Index: 7398411 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.5552. Min Act: -0.1700
Data Index: 7329569 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.5552. Min Act: -0.1700
Data Index: 4434504 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1177. Min Range: -9.1177
Max Act: 8.6177. Min Act: -0.1700
Data Index: 2002806 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19