Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2356 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4460. Min Range: -6.4460
Max Act: 6.4460. Min Act: -0.1700
Data Index: 4340576 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4460. Min Range: -6.4460
Max Act: 6.1960. Min Act: -0.1700
Data Index: 332472 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4460. Min Range: -6.4460
Max Act: 6.1960. Min Act: -0.1700
Data Index: 1987725 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4460. Min Range: -6.4460
Max Act: 6.0710. Min Act: -0.1700
Data Index: 6939746 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4460. Min Range: -6.4460
Max Act: 6.0397. Min Act: -0.1700
Data Index: 5531739 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4460. Min Range: -6.4460
Max Act: 5.9147. Min Act: -0.1700
Data Index: 6214095 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4460. Min Range: -6.4460
Max Act: 5.9147. Min Act: -0.1700
Data Index: 1328107 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4460. Min Range: -6.4460
Max Act: 5.8835. Min Act: -0.1700
Data Index: 7887123 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4460. Min Range: -6.4460
Max Act: 5.8210. Min Act: -0.1700
Data Index: 7234941 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4460. Min Range: -6.4460
Max Act: 5.7585. Min Act: -0.1700
Data Index: 7887132 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4460. Min Range: -6.4460
Max Act: 5.7272. Min Act: -0.1700
Data Index: 6113589 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4460. Min Range: -6.4460
Max Act: 5.6960. Min Act: -0.1700
Data Index: 6606860 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4460. Min Range: -6.4460
Max Act: 5.6960. Min Act: -0.1700
Data Index: 6939729 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4460. Min Range: -6.4460
Max Act: 5.6960. Min Act: -0.1700
Data Index: 3048950 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4460. Min Range: -6.4460
Max Act: 5.6647. Min Act: -0.1700
Data Index: 332475 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4460. Min Range: -6.4460
Max Act: 5.6960. Min Act: -0.1700
Data Index: 1167777 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4460. Min Range: -6.4460
Max Act: 5.6647. Min Act: -0.1700
Data Index: 6214094 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4460. Min Range: -6.4460
Max Act: 5.6335. Min Act: -0.1700
Data Index: 1987724 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4460. Min Range: -6.4460
Max Act: 5.6022. Min Act: -0.1700
Data Index: 7887122 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4460. Min Range: -6.4460
Max Act: 5.5710. Min Act: -0.1700
Data Index: 8196458 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19