Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3397 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.8387. Min Act: -0.1700
Data Index: 7189425 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.5884. Min Act: -0.1700
Data Index: 2896805 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.5727. Min Act: -0.1700
Data Index: 3837069 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.5414. Min Act: -0.1700
Data Index: 5339139 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.5258. Min Act: -0.1700
Data Index: 8250646 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.4944. Min Act: -0.1700
Data Index: 4703537 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.4944. Min Act: -0.1700
Data Index: 7835744 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.4788. Min Act: -0.1700
Data Index: 7413678 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.4788. Min Act: -0.1700
Data Index: 7324592 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.4788. Min Act: -0.1700
Data Index: 6348173 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.4474. Min Act: -0.1700
Data Index: 310046 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.4474. Min Act: -0.1700
Data Index: 470473 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.4474. Min Act: -0.1700
Data Index: 2025922 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.3847. Min Act: -0.1700
Data Index: 2959466 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.3847. Min Act: -0.1700
Data Index: 7561415 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.3847. Min Act: -0.1700
Data Index: 2480533 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.3847. Min Act: -0.1700
Data Index: 2697463 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.3691. Min Act: -0.1700
Data Index: 5011174 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.3691. Min Act: -0.1700
Data Index: 1827738 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8387. Min Range: -3.8387
Max Act: 3.3691. Min Act: -0.1700
Data Index: 318578 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19