Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3974 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.6057. Min Act: -0.1700
Data Index: 4605632 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.6057. Min Act: -0.1700
Data Index: 2992467 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.4807. Min Act: -0.1700
Data Index: 2521451 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.3869. Min Act: -0.1700
Data Index: 6815989 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.3869. Min Act: -0.1700
Data Index: 8666081 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.3869. Min Act: -0.1700
Data Index: 7974047 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.3869. Min Act: -0.1700
Data Index: 5019826 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.3244. Min Act: -0.1700
Data Index: 4516959 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.3557. Min Act: -0.1700
Data Index: 6708962 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.3244. Min Act: -0.1700
Data Index: 1618810 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.3557. Min Act: -0.1700
Data Index: 309650 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.2932. Min Act: -0.1700
Data Index: 6563343 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.3244. Min Act: -0.1700
Data Index: 1571911 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.3244. Min Act: -0.1700
Data Index: 2190680 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.3244. Min Act: -0.1700
Data Index: 146033 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.2932. Min Act: -0.1700
Data Index: 6689005 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.2932. Min Act: -0.1700
Data Index: 7548362 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.2619. Min Act: -0.1700
Data Index: 1756322 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.2932. Min Act: -0.1700
Data Index: 3643486 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6057. Min Range: -5.6057
Max Act: 5.2932. Min Act: -0.1700
Data Index: 93555 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19