Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2218 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5551. Min Range: -5.5551
Max Act: 5.5551. Min Act: -0.1700
Data Index: 2801502 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5551. Min Range: -5.5551
Max Act: 5.2739. Min Act: -0.1700
Data Index: 6736220 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5551. Min Range: -5.5551
Max Act: 5.2739. Min Act: -0.1700
Data Index: 8427371 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5551. Min Range: -5.5551
Max Act: 5.2739. Min Act: -0.1700
Data Index: 159555 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5551. Min Range: -5.5551
Max Act: 5.2739. Min Act: -0.1700
Data Index: 543169 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5551. Min Range: -5.5551
Max Act: 5.2426. Min Act: -0.1700
Data Index: 5455041 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5551. Min Range: -5.5551
Max Act: 5.2114. Min Act: -0.1700
Data Index: 6424678 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5551. Min Range: -5.5551
Max Act: 5.1176. Min Act: -0.1700
Data Index: 8594025 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5551. Min Range: -5.5551
Max Act: 5.1176. Min Act: -0.1700
Data Index: 629040 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5551. Min Range: -5.5551
Max Act: 5.0239. Min Act: -0.1700
Data Index: 1619595 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5551. Min Range: -5.5551
Max Act: 5.0239. Min Act: -0.1700
Data Index: 8049824 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5551. Min Range: -5.5551
Max Act: 5.0551. Min Act: -0.1700
Data Index: 5413326 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5551. Min Range: -5.5551
Max Act: 5.0239. Min Act: -0.1700
Data Index: 8040501 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5551. Min Range: -5.5551
Max Act: 4.9926. Min Act: -0.1700
Data Index: 5074037 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5551. Min Range: -5.5551
Max Act: 4.9926. Min Act: -0.1700
Data Index: 7003665 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5551. Min Range: -5.5551
Max Act: 4.9614. Min Act: -0.1700
Data Index: 5463678 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5551. Min Range: -5.5551
Max Act: 4.9926. Min Act: -0.1700
Data Index: 980647 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5551. Min Range: -5.5551
Max Act: 4.9614. Min Act: -0.1700
Data Index: 6142398 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5551. Min Range: -5.5551
Max Act: 4.9614. Min Act: -0.1700
Data Index: 3044003 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5551. Min Range: -5.5551
Max Act: 4.9614. Min Act: -0.1700
Data Index: 1481015 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19