Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2918 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0243. Min Range: -11.0243
Max Act: 11.0243. Min Act: -0.1700
Data Index: 5689663 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.9618. Min Act: -0.1700
Data Index: 4366879 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.8993. Min Act: -0.1700
Data Index: 5689662 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.7743. Min Act: -0.1700
Data Index: 1626350 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.5868. Min Act: -0.1700
Data Index: 4531159 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.5868. Min Act: -0.1700
Data Index: 4077550 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.3993. Min Act: -0.1700
Data Index: 4241682 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.3993. Min Act: -0.1700
Data Index: 5075307 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.3368. Min Act: -0.1700
Data Index: 804908 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.3368. Min Act: -0.1700
Data Index: 1341878 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.3368. Min Act: -0.1700
Data Index: 2435545 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.2743. Min Act: -0.1700
Data Index: 6493848 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.2118. Min Act: -0.1700
Data Index: 4876934 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.2118. Min Act: -0.1700
Data Index: 4817474 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.2118. Min Act: -0.1700
Data Index: 1553610 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.2118. Min Act: -0.1700
Data Index: 1968106 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.1493. Min Act: -0.1700
Data Index: 3266969 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.1493. Min Act: -0.1700
Data Index: 2242471 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.1493. Min Act: -0.1700
Data Index: 5170959 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0243. Min Range: -11.0243
Max Act: 10.1493. Min Act: -0.1700
Data Index: 143602 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19