Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3341 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0974. Min Range: -9.0974
Max Act: 9.0974. Min Act: -0.1700
Data Index: 1413050 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.7224. Min Act: -0.1700
Data Index: 4378073 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.6599. Min Act: -0.1700
Data Index: 2406856 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.5974. Min Act: -0.1700
Data Index: 1762840 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.4724. Min Act: -0.1700
Data Index: 382497 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.4099. Min Act: -0.1700
Data Index: 8246387 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.4099. Min Act: -0.1700
Data Index: 6506335 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.3474. Min Act: -0.1700
Data Index: 4090393 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.2224. Min Act: -0.1700
Data Index: 3968953 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.1599. Min Act: -0.1700
Data Index: 6261351 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.0974. Min Act: -0.1700
Data Index: 890507 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.0974. Min Act: -0.1700
Data Index: 2611993 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.0662. Min Act: -0.1700
Data Index: 4603492 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.0974. Min Act: -0.1700
Data Index: 6435403 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.0974. Min Act: -0.1700
Data Index: 1213941 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.0349. Min Act: -0.1700
Data Index: 8022071 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.0662. Min Act: -0.1700
Data Index: 1624572 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.0662. Min Act: -0.1700
Data Index: 4971964 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.0349. Min Act: -0.1700
Data Index: 7022211 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0974. Min Range: -9.0974
Max Act: 8.0037. Min Act: -0.1700
Data Index: 86163 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19