Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2942 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0186. Min Range: -3.0186
Max Act: 3.0186. Min Act: -0.1700
Data Index: 1816112 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.9869. Min Act: -0.1700
Data Index: 3893892 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.9236. Min Act: -0.1700
Data Index: 5025497 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.9078. Min Act: -0.1700
Data Index: 3625080 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.8919. Min Act: -0.1700
Data Index: 3716571 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.9236. Min Act: -0.1700
Data Index: 4619624 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.8919. Min Act: -0.1700
Data Index: 1543417 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.8761. Min Act: -0.1700
Data Index: 8232452 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.8919. Min Act: -0.1700
Data Index: 6097373 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.8761. Min Act: -0.1700
Data Index: 5591609 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.8919. Min Act: -0.1700
Data Index: 253618 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.8761. Min Act: -0.1700
Data Index: 7280900 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.8443. Min Act: -0.1700
Data Index: 8716223 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.8761. Min Act: -0.1700
Data Index: 7855584 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.8602. Min Act: -0.1700
Data Index: 2077372 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.8284. Min Act: -0.1700
Data Index: 3765190 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.8284. Min Act: -0.1700
Data Index: 6843953 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.8284. Min Act: -0.1700
Data Index: 7566943 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.8443. Min Act: -0.1700
Data Index: 5061412 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0186. Min Range: -3.0186
Max Act: 2.8443. Min Act: -0.1700
Data Index: 5373258 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19