Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3071 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3850. Min Range: -4.3850
Max Act: 4.3225. Min Act: -0.1700
Data Index: 4306002 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3850. Min Range: -4.3850
Max Act: 4.3850. Min Act: -0.1700
Data Index: 4607719 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3850. Min Range: -4.3850
Max Act: 4.2912. Min Act: -0.1700
Data Index: 214120 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3850. Min Range: -4.3850
Max Act: 4.1975. Min Act: -0.1700
Data Index: 6873172 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3850. Min Range: -4.3850
Max Act: 4.1037. Min Act: -0.1700
Data Index: 3930314 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3850. Min Range: -4.3850
Max Act: 4.1350. Min Act: -0.1700
Data Index: 2226210 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3850. Min Range: -4.3850
Max Act: 4.1037. Min Act: -0.1700
Data Index: 7500636 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3850. Min Range: -4.3850
Max Act: 4.1037. Min Act: -0.1700
Data Index: 561315 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3850. Min Range: -4.3850
Max Act: 4.0724. Min Act: -0.1700
Data Index: 4607716 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3850. Min Range: -4.3850
Max Act: 4.0724. Min Act: -0.1700
Data Index: 8536632 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3850. Min Range: -4.3850
Max Act: 4.0724. Min Act: -0.1700
Data Index: 3280702 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3850. Min Range: -4.3850
Max Act: 4.0724. Min Act: -0.1700
Data Index: 5321538 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3850. Min Range: -4.3850
Max Act: 4.0412. Min Act: -0.1700
Data Index: 4394903 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3850. Min Range: -4.3850
Max Act: 4.0412. Min Act: -0.1700
Data Index: 4607715 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3850. Min Range: -4.3850
Max Act: 4.0412. Min Act: -0.1700
Data Index: 632798 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3850. Min Range: -4.3850
Max Act: 4.0099. Min Act: -0.1700
Data Index: 5700850 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3850. Min Range: -4.3850
Max Act: 4.0099. Min Act: -0.1700
Data Index: 214119 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3850. Min Range: -4.3850
Max Act: 4.0099. Min Act: -0.1700
Data Index: 214122 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3850. Min Range: -4.3850
Max Act: 3.9474. Min Act: -0.1700
Data Index: 395693 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3850. Min Range: -4.3850
Max Act: 3.9787. Min Act: -0.1700
Data Index: 366103 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19