Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4653 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.7202. Min Act: -0.1700
Data Index: 427217 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.4702. Min Act: -0.1700
Data Index: 2475273 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.4390. Min Act: -0.1700
Data Index: 4323579 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.4077. Min Act: -0.1700
Data Index: 7464484 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.3452. Min Act: -0.1700
Data Index: 7870354 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.3452. Min Act: -0.1700
Data Index: 5249614 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.2827. Min Act: -0.1700
Data Index: 6002103 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.2514. Min Act: -0.1700
Data Index: 515771 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.2514. Min Act: -0.1700
Data Index: 5272736 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.2202. Min Act: -0.1700
Data Index: 5155386 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.2202. Min Act: -0.1700
Data Index: 4803757 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.1889. Min Act: -0.1700
Data Index: 7138316 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.1889. Min Act: -0.1700
Data Index: 6142105 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.1889. Min Act: -0.1700
Data Index: 3730858 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.1577. Min Act: -0.1700
Data Index: 5865085 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.1889. Min Act: -0.1700
Data Index: 189398 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.2202. Min Act: -0.1700
Data Index: 6977405 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.1889. Min Act: -0.1700
Data Index: 6650309 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.1577. Min Act: -0.1700
Data Index: 655882 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7202. Min Range: -4.7202
Max Act: 4.1577. Min Act: -0.1700
Data Index: 7208001 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19