Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3185 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.7113. Min Act: -0.1700
Data Index: 1023801 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.6488. Min Act: -0.1700
Data Index: 4150494 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.6176. Min Act: -0.1700
Data Index: 1473277 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.5551. Min Act: -0.1700
Data Index: 2004641 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.5238. Min Act: -0.1700
Data Index: 8823747 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.4926. Min Act: -0.1700
Data Index: 5380189 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.4926. Min Act: -0.1700
Data Index: 262131 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.4613. Min Act: -0.1700
Data Index: 4582576 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.4613. Min Act: -0.1700
Data Index: 3000389 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.4301. Min Act: -0.1700
Data Index: 3234334 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.3988. Min Act: -0.1700
Data Index: 3080067 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.4301. Min Act: -0.1700
Data Index: 6747868 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.3988. Min Act: -0.1700
Data Index: 484960 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.3988. Min Act: -0.1700
Data Index: 7146019 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.4301. Min Act: -0.1700
Data Index: 7508719 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.3988. Min Act: -0.1700
Data Index: 5968046 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.3676. Min Act: -0.1700
Data Index: 7263347 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.3676. Min Act: -0.1700
Data Index: 2438018 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.3676. Min Act: -0.1700
Data Index: 4075391 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7113. Min Range: -4.7113
Max Act: 4.3676. Min Act: -0.1700
Data Index: 5875139 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19