Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2326 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7012. Min Range: -5.7012
Max Act: 5.7012. Min Act: -0.1700
Data Index: 7952645 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7012. Min Range: -5.7012
Max Act: 5.2012. Min Act: -0.1700
Data Index: 4822850 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7012. Min Range: -5.7012
Max Act: 5.1700. Min Act: -0.1700
Data Index: 4820832 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7012. Min Range: -5.7012
Max Act: 5.0762. Min Act: -0.1700
Data Index: 8184497 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7012. Min Range: -5.7012
Max Act: 5.0762. Min Act: -0.1700
Data Index: 572698 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7012. Min Range: -5.7012
Max Act: 5.0450. Min Act: -0.1700
Data Index: 4167321 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7012. Min Range: -5.7012
Max Act: 5.0450. Min Act: -0.1700
Data Index: 417858 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7012. Min Range: -5.7012
Max Act: 5.0450. Min Act: -0.1700
Data Index: 3680325 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7012. Min Range: -5.7012
Max Act: 4.9200. Min Act: -0.1700
Data Index: 2529725 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7012. Min Range: -5.7012
Max Act: 4.9200. Min Act: -0.1700
Data Index: 6585745 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7012. Min Range: -5.7012
Max Act: 4.9825. Min Act: -0.1700
Data Index: 3068434 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7012. Min Range: -5.7012
Max Act: 5.0137. Min Act: -0.1700
Data Index: 3080167 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7012. Min Range: -5.7012
Max Act: 4.8575. Min Act: -0.1700
Data Index: 1969162 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7012. Min Range: -5.7012
Max Act: 4.8262. Min Act: -0.1700
Data Index: 7237086 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7012. Min Range: -5.7012
Max Act: 4.8575. Min Act: -0.1700
Data Index: 1307947 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7012. Min Range: -5.7012
Max Act: 4.8887. Min Act: -0.1700
Data Index: 6327327 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7012. Min Range: -5.7012
Max Act: 4.8575. Min Act: -0.1700
Data Index: 6201058 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7012. Min Range: -5.7012
Max Act: 4.7950. Min Act: -0.1700
Data Index: 304410 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7012. Min Range: -5.7012
Max Act: 4.8262. Min Act: -0.1700
Data Index: 5177819 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7012. Min Range: -5.7012
Max Act: 4.8262. Min Act: -0.1700
Data Index: 5107496 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19