Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3434 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.4849. Min Act: -0.1700
Data Index: 6115794 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.3911. Min Act: -0.1700
Data Index: 8790329 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.3599. Min Act: -0.1700
Data Index: 993592 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.3599. Min Act: -0.1700
Data Index: 776422 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.2974. Min Act: -0.1700
Data Index: 4124569 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.2349. Min Act: -0.1700
Data Index: 1223510 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.2349. Min Act: -0.1700
Data Index: 6132496 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.1724. Min Act: -0.1700
Data Index: 1839672 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.1411. Min Act: -0.1700
Data Index: 4389389 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.1411. Min Act: -0.1700
Data Index: 8667387 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.1411. Min Act: -0.1700
Data Index: 6847384 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.1411. Min Act: -0.1700
Data Index: 4606764 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.1099. Min Act: -0.1700
Data Index: 7927198 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.1099. Min Act: -0.1700
Data Index: 6312430 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.1099. Min Act: -0.1700
Data Index: 4474030 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.1099. Min Act: -0.1700
Data Index: 6211082 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.1099. Min Act: -0.1700
Data Index: 384322 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.1411. Min Act: -0.1700
Data Index: 3762370 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.1099. Min Act: -0.1700
Data Index: 6837179 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4849. Min Range: -6.4849
Max Act: 6.0474. Min Act: -0.1700
Data Index: 2836756 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19