Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1244 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.5509. Min Act: -0.1700
Data Index: 7324934 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.4099. Min Act: -0.1700
Data Index: 2329210 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.3942. Min Act: -0.1700
Data Index: 517236 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.3942. Min Act: -0.1700
Data Index: 1210050 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.3158. Min Act: -0.1700
Data Index: 5627244 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.3158. Min Act: -0.1700
Data Index: 3003122 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.2844. Min Act: -0.1700
Data Index: 1426443 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.2687. Min Act: -0.1700
Data Index: 7162314 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.2216. Min Act: -0.1700
Data Index: 2683889 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.1586. Min Act: -0.1700
Data Index: 7743282 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.1744. Min Act: -0.1700
Data Index: 5033811 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.1744. Min Act: -0.1700
Data Index: 8038576 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.1586. Min Act: -0.1700
Data Index: 2745059 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.1586. Min Act: -0.1700
Data Index: 4746896 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.1429. Min Act: -0.1700
Data Index: 2592856 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.1271. Min Act: -0.1700
Data Index: 3995465 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.1429. Min Act: -0.1700
Data Index: 6749302 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.1114. Min Act: -0.1700
Data Index: 5489207 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.1271. Min Act: -0.1700
Data Index: 3628960 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5509. Min Range: -3.5509
Max Act: 3.1271. Min Act: -0.1700
Data Index: 7411417 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19