Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3513 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.2811. Min Range: -9.2811
Max Act: 9.2811. Min Act: -0.1700
Data Index: 5108203 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2811. Min Range: -9.2811
Max Act: 9.1561. Min Act: -0.1700
Data Index: 8666888 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2811. Min Range: -9.2811
Max Act: 9.1561. Min Act: -0.1700
Data Index: 5986670 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2811. Min Range: -9.2811
Max Act: 9.1561. Min Act: -0.1700
Data Index: 112641 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2811. Min Range: -9.2811
Max Act: 9.0936. Min Act: -0.1700
Data Index: 1868575 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2811. Min Range: -9.2811
Max Act: 9.0311. Min Act: -0.1700
Data Index: 2327683 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2811. Min Range: -9.2811
Max Act: 8.9686. Min Act: -0.1700
Data Index: 5737 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2811. Min Range: -9.2811
Max Act: 8.9686. Min Act: -0.1700
Data Index: 8188944 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2811. Min Range: -9.2811
Max Act: 8.9061. Min Act: -0.1700
Data Index: 2662499 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2811. Min Range: -9.2811
Max Act: 8.8436. Min Act: -0.1700
Data Index: 3205171 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2811. Min Range: -9.2811
Max Act: 8.9061. Min Act: -0.1700
Data Index: 3899287 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2811. Min Range: -9.2811
Max Act: 8.8436. Min Act: -0.1700
Data Index: 2088490 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2811. Min Range: -9.2811
Max Act: 8.8436. Min Act: -0.1700
Data Index: 578711 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2811. Min Range: -9.2811
Max Act: 8.7811. Min Act: -0.1700
Data Index: 6243578 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2811. Min Range: -9.2811
Max Act: 8.7811. Min Act: -0.1700
Data Index: 8802104 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2811. Min Range: -9.2811
Max Act: 8.7811. Min Act: -0.1700
Data Index: 6538243 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2811. Min Range: -9.2811
Max Act: 8.7811. Min Act: -0.1700
Data Index: 6570286 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2811. Min Range: -9.2811
Max Act: 8.7811. Min Act: -0.1700
Data Index: 3496432 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2811. Min Range: -9.2811
Max Act: 8.7811. Min Act: -0.1700
Data Index: 6736957 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2811. Min Range: -9.2811
Max Act: 8.7186. Min Act: -0.1700
Data Index: 7332174 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19