Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3893 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.5149. Min Act: -0.1700
Data Index: 4076939 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.2649. Min Act: -0.1700
Data Index: 5937912 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.2336. Min Act: -0.1700
Data Index: 3928447 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.2336. Min Act: -0.1700
Data Index: 3859420 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.2336. Min Act: -0.1700
Data Index: 3684646 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.2024. Min Act: -0.1700
Data Index: 3266347 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.1711. Min Act: -0.1700
Data Index: 4223223 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.1711. Min Act: -0.1700
Data Index: 5949327 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.1399. Min Act: -0.1700
Data Index: 8343883 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.1086. Min Act: -0.1700
Data Index: 495383 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.1399. Min Act: -0.1700
Data Index: 5237799 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.1086. Min Act: -0.1700
Data Index: 8827728 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.1086. Min Act: -0.1700
Data Index: 4538601 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.0774. Min Act: -0.1700
Data Index: 8571852 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.1086. Min Act: -0.1700
Data Index: 2771102 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.1399. Min Act: -0.1700
Data Index: 1746650 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.1086. Min Act: -0.1700
Data Index: 690670 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.1086. Min Act: -0.1700
Data Index: 112508 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.0774. Min Act: -0.1700
Data Index: 7308353 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5149. Min Range: -5.5149
Max Act: 5.0774. Min Act: -0.1700
Data Index: 2810096 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19