Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 165 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.2682. Min Act: -0.1700
Data Index: 4077923 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1744. Min Act: -0.1700
Data Index: 1219527 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1432. Min Act: -0.1700
Data Index: 7261873 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1432. Min Act: -0.1700
Data Index: 3129580 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1119. Min Act: -0.1700
Data Index: 1489840 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1119. Min Act: -0.1700
Data Index: 5970985 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0494. Min Act: -0.1700
Data Index: 7547854 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0182. Min Act: -0.1700
Data Index: 6528972 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0182. Min Act: -0.1700
Data Index: 4601306 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.9557. Min Act: -0.1700
Data Index: 2703705 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0494. Min Act: -0.1700
Data Index: 1177944 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.9557. Min Act: -0.1700
Data Index: 3340923 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.9557. Min Act: -0.1700
Data Index: 2368935 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.9557. Min Act: -0.1700
Data Index: 499149 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.9244. Min Act: -0.1700
Data Index: 3876192 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.9244. Min Act: -0.1700
Data Index: 1499398 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.9244. Min Act: -0.1700
Data Index: 1900144 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.8619. Min Act: -0.1700
Data Index: 4610241 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.8932. Min Act: -0.1700
Data Index: 4927983 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.8619. Min Act: -0.1700
Data Index: 6027267 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19