Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3570 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.2328. Min Act: -0.1700
Data Index: 5962765 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.2015. Min Act: -0.1700
Data Index: 3255937 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.2015. Min Act: -0.1700
Data Index: 6593163 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.1703. Min Act: -0.1700
Data Index: 2210784 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.1703. Min Act: -0.1700
Data Index: 4382972 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.1390. Min Act: -0.1700
Data Index: 2288194 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.1390. Min Act: -0.1700
Data Index: 2515220 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.1390. Min Act: -0.1700
Data Index: 4875435 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.1703. Min Act: -0.1700
Data Index: 5786572 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.1078. Min Act: -0.1700
Data Index: 1584048 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.1078. Min Act: -0.1700
Data Index: 3733775 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.1078. Min Act: -0.1700
Data Index: 8725823 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.1078. Min Act: -0.1700
Data Index: 7985364 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.1078. Min Act: -0.1700
Data Index: 353255 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.1078. Min Act: -0.1700
Data Index: 4404690 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.1078. Min Act: -0.1700
Data Index: 1246541 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.1078. Min Act: -0.1700
Data Index: 4382227 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.1078. Min Act: -0.1700
Data Index: 4241782 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.1078. Min Act: -0.1700
Data Index: 3888740 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2328. Min Range: -5.2328
Max Act: 5.0765. Min Act: -0.1700
Data Index: 201270 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19