Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1861 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.6377. Min Act: -0.1700
Data Index: 8585256 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.6064. Min Act: -0.1700
Data Index: 4812861 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.5439. Min Act: -0.1700
Data Index: 8507145 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.5752. Min Act: -0.1700
Data Index: 7727928 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.5127. Min Act: -0.1700
Data Index: 8309003 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.5439. Min Act: -0.1700
Data Index: 4170164 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.5127. Min Act: -0.1700
Data Index: 4753621 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.5127. Min Act: -0.1700
Data Index: 3754766 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.5127. Min Act: -0.1700
Data Index: 4887213 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.5127. Min Act: -0.1700
Data Index: 8614170 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.5127. Min Act: -0.1700
Data Index: 5295261 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.5127. Min Act: -0.1700
Data Index: 5454966 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.5127. Min Act: -0.1700
Data Index: 2625126 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.4502. Min Act: -0.1700
Data Index: 7827291 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.4814. Min Act: -0.1700
Data Index: 2771236 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.4502. Min Act: -0.1700
Data Index: 6265588 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.4814. Min Act: -0.1700
Data Index: 4717328 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.4814. Min Act: -0.1700
Data Index: 4536900 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.4814. Min Act: -0.1700
Data Index: 4527391 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6377. Min Range: -4.6377
Max Act: 4.4814. Min Act: -0.1700
Data Index: 4093720 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19