Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1413 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4916. Min Range: -10.4916
Max Act: 10.4916. Min Act: -0.1700
Data Index: 6421290 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4916. Min Range: -10.4916
Max Act: 10.3041. Min Act: -0.1700
Data Index: 218848 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4916. Min Range: -10.4916
Max Act: 9.9916. Min Act: -0.1700
Data Index: 6577611 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4916. Min Range: -10.4916
Max Act: 10.0541. Min Act: -0.1700
Data Index: 1489137 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4916. Min Range: -10.4916
Max Act: 9.9916. Min Act: -0.1700
Data Index: 8694053 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4916. Min Range: -10.4916
Max Act: 9.9916. Min Act: -0.1700
Data Index: 1072176 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4916. Min Range: -10.4916
Max Act: 9.9291. Min Act: -0.1700
Data Index: 437522 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4916. Min Range: -10.4916
Max Act: 9.8666. Min Act: -0.1700
Data Index: 4412526 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4916. Min Range: -10.4916
Max Act: 9.8041. Min Act: -0.1700
Data Index: 967000 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4916. Min Range: -10.4916
Max Act: 9.8041. Min Act: -0.1700
Data Index: 4703633 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4916. Min Range: -10.4916
Max Act: 9.7416. Min Act: -0.1700
Data Index: 5175174 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4916. Min Range: -10.4916
Max Act: 9.7416. Min Act: -0.1700
Data Index: 7388888 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4916. Min Range: -10.4916
Max Act: 9.7416. Min Act: -0.1700
Data Index: 8681235 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4916. Min Range: -10.4916
Max Act: 9.6791. Min Act: -0.1700
Data Index: 6717872 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4916. Min Range: -10.4916
Max Act: 9.6791. Min Act: -0.1700
Data Index: 4305161 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4916. Min Range: -10.4916
Max Act: 9.6791. Min Act: -0.1700
Data Index: 1907755 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4916. Min Range: -10.4916
Max Act: 9.6791. Min Act: -0.1700
Data Index: 5711816 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4916. Min Range: -10.4916
Max Act: 9.6166. Min Act: -0.1700
Data Index: 1575744 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4916. Min Range: -10.4916
Max Act: 9.6166. Min Act: -0.1700
Data Index: 1040443 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4916. Min Range: -10.4916
Max Act: 9.5541. Min Act: -0.1700
Data Index: 4449577 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19