Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3146 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.3017. Min Act: -0.1700
Data Index: 4320007 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.3017. Min Act: -0.1699
Data Index: 126846 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.2079. Min Act: -0.1700
Data Index: 6699188 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.2079. Min Act: -0.1700
Data Index: 909293 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1767. Min Act: -0.1699
Data Index: 8679232 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1767. Min Act: -0.1700
Data Index: 7560326 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1767. Min Act: -0.1700
Data Index: 1099776 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1767. Min Act: -0.1700
Data Index: 8387474 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1767. Min Act: -0.1700
Data Index: 3942468 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.2079. Min Act: -0.1700
Data Index: 8248033 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1767. Min Act: -0.1700
Data Index: 2997630 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1454. Min Act: -0.1700
Data Index: 4613023 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1454. Min Act: -0.1700
Data Index: 8766267 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1454. Min Act: -0.1700
Data Index: 8245450 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1454. Min Act: -0.1700
Data Index: 7687141 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1454. Min Act: -0.1700
Data Index: 6892239 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1767. Min Act: -0.1700
Data Index: 3186783 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1454. Min Act: -0.1700
Data Index: 219623 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1454. Min Act: -0.1700
Data Index: 5999641 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1142. Min Act: -0.1700
Data Index: 4770195 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19