Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5223 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.8254. Min Act: -0.1700
Data Index: 1182520 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.6067. Min Act: -0.1700
Data Index: 2493837 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.4192. Min Act: -0.1700
Data Index: 5339594 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.3567. Min Act: -0.1700
Data Index: 624175 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.2942. Min Act: -0.1700
Data Index: 8675988 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.2942. Min Act: -0.1700
Data Index: 6190233 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.2317. Min Act: -0.1700
Data Index: 3789641 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.2004. Min Act: -0.1700
Data Index: 4870294 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.2004. Min Act: -0.1700
Data Index: 5365299 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.1692. Min Act: -0.1700
Data Index: 4715706 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.1692. Min Act: -0.1700
Data Index: 3760229 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.1692. Min Act: -0.1700
Data Index: 7472210 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.1379. Min Act: -0.1700
Data Index: 1278616 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.1067. Min Act: -0.1700
Data Index: 7963076 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.1067. Min Act: -0.1700
Data Index: 1476151 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.1067. Min Act: -0.1700
Data Index: 8078296 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.0754. Min Act: -0.1700
Data Index: 7078777 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.0754. Min Act: -0.1700
Data Index: 6662948 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.0442. Min Act: -0.1700
Data Index: 3920788 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8254. Min Range: -6.8254
Max Act: 6.0754. Min Act: -0.1700
Data Index: 35517 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19