Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2237 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.9590. Min Act: -0.1700
Data Index: 6998381 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.8653. Min Act: -0.1700
Data Index: 2553399 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.8183. Min Act: -0.1700
Data Index: 2772895 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.7402. Min Act: -0.1700
Data Index: 8321758 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.7245. Min Act: -0.1700
Data Index: 8505448 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.7089. Min Act: -0.1700
Data Index: 5970204 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.7089. Min Act: -0.1700
Data Index: 8764704 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.6776. Min Act: -0.1700
Data Index: 8811367 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.6776. Min Act: -0.1700
Data Index: 8081967 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.6619. Min Act: -0.1700
Data Index: 1903953 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.6306. Min Act: -0.1700
Data Index: 7095815 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.6150. Min Act: -0.1700
Data Index: 7619959 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.5993. Min Act: -0.1700
Data Index: 1024495 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.5993. Min Act: -0.1700
Data Index: 2384157 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.5993. Min Act: -0.1700
Data Index: 2242864 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.5993. Min Act: -0.1700
Data Index: 7292114 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.5993. Min Act: -0.1700
Data Index: 5949700 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.5993. Min Act: -0.1700
Data Index: 617977 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.5837. Min Act: -0.1700
Data Index: 5085881 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9590. Min Range: -3.9590
Max Act: 3.5837. Min Act: -0.1700
Data Index: 4529978 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19