Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.1774. Min Act: -0.1700
Data Index: 5220639 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.1616. Min Act: -0.1700
Data Index: 5594627 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.1302. Min Act: -0.1700
Data Index: 7169405 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.1144. Min Act: -0.1700
Data Index: 769733 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.0829. Min Act: -0.1700
Data Index: 6888776 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.1144. Min Act: -0.1700
Data Index: 5849473 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.0671. Min Act: -0.1700
Data Index: 1086790 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.0513. Min Act: -0.1700
Data Index: 3069806 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.0040. Min Act: -0.1700
Data Index: 1292689 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.0040. Min Act: -0.1700
Data Index: 158085 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.0198. Min Act: -0.1700
Data Index: 4223805 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.0198. Min Act: -0.1700
Data Index: 7571466 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.0198. Min Act: -0.1700
Data Index: 576183 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.0040. Min Act: -0.1700
Data Index: 973247 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.0198. Min Act: -0.1700
Data Index: 2801695 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.0040. Min Act: -0.1699
Data Index: 5593255 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1774. Min Range: -3.1774
Max Act: 2.9723. Min Act: -0.1700
Data Index: 431790 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.0040. Min Act: -0.1700
Data Index: 2958810 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.0040. Min Act: -0.1700
Data Index: 475053 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1774. Min Range: -3.1774
Max Act: 3.0040. Min Act: -0.1700
Data Index: 7463630 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19