Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1178 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4283. Min Range: -7.4283
Max Act: 7.4283. Min Act: -0.1700
Data Index: 4294592 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4283. Min Range: -7.4283
Max Act: 7.1783. Min Act: -0.1700
Data Index: 4273016 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4283. Min Range: -7.4283
Max Act: 7.0220. Min Act: -0.1700
Data Index: 34740 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4283. Min Range: -7.4283
Max Act: 6.9908. Min Act: -0.1700
Data Index: 6803370 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4283. Min Range: -7.4283
Max Act: 6.9283. Min Act: -0.1700
Data Index: 4520340 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4283. Min Range: -7.4283
Max Act: 6.8970. Min Act: -0.1700
Data Index: 1627322 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4283. Min Range: -7.4283
Max Act: 6.8345. Min Act: -0.1700
Data Index: 8299354 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4283. Min Range: -7.4283
Max Act: 6.8033. Min Act: -0.1700
Data Index: 56507 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4283. Min Range: -7.4283
Max Act: 6.7720. Min Act: -0.1700
Data Index: 6737175 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4283. Min Range: -7.4283
Max Act: 6.7095. Min Act: -0.1700
Data Index: 5814487 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4283. Min Range: -7.4283
Max Act: 6.7095. Min Act: -0.1700
Data Index: 4962305 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4283. Min Range: -7.4283
Max Act: 6.6158. Min Act: -0.1700
Data Index: 5912934 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4283. Min Range: -7.4283
Max Act: 6.6158. Min Act: -0.1700
Data Index: 1065533 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4283. Min Range: -7.4283
Max Act: 6.6158. Min Act: -0.1700
Data Index: 8384511 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4283. Min Range: -7.4283
Max Act: 6.5845. Min Act: -0.1700
Data Index: 6151733 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4283. Min Range: -7.4283
Max Act: 6.5845. Min Act: -0.1700
Data Index: 2527657 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4283. Min Range: -7.4283
Max Act: 6.5220. Min Act: -0.1700
Data Index: 599961 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4283. Min Range: -7.4283
Max Act: 6.5220. Min Act: -0.1700
Data Index: 38970 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4283. Min Range: -7.4283
Max Act: 6.4908. Min Act: -0.1700
Data Index: 7892414 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4283. Min Range: -7.4283
Max Act: 6.4908. Min Act: -0.1700
Data Index: 5053102 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19