Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3950 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.3279. Min Act: -0.1700
Data Index: 7119086 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.3591. Min Act: -0.1700
Data Index: 4292586 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.2966. Min Act: -0.1700
Data Index: 900234 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.2654. Min Act: -0.1700
Data Index: 4941864 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.2029. Min Act: -0.1700
Data Index: 3023643 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.2029. Min Act: -0.1700
Data Index: 6596970 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.2029. Min Act: -0.1700
Data Index: 4960943 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.1404. Min Act: -0.1700
Data Index: 391168 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.1716. Min Act: -0.1700
Data Index: 5656224 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.1404. Min Act: -0.1700
Data Index: 1263567 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.1404. Min Act: -0.1700
Data Index: 8106845 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.1404. Min Act: -0.1700
Data Index: 338095 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.1091. Min Act: -0.1700
Data Index: 5127270 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.0779. Min Act: -0.1700
Data Index: 4270806 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.1091. Min Act: -0.1700
Data Index: 2424311 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.1091. Min Act: -0.1700
Data Index: 4837759 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.0779. Min Act: -0.1700
Data Index: 1481000 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.1091. Min Act: -0.1700
Data Index: 7822190 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.0466. Min Act: -0.1700
Data Index: 4368911 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3591. Min Range: -5.3591
Max Act: 5.0466. Min Act: -0.1700
Data Index: 6316072 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19