Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 483 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.9337. Min Act: -0.1700
Data Index: 6335200 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.8399. Min Act: -0.1700
Data Index: 834368 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.8086. Min Act: -0.1700
Data Index: 3026612 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.7773. Min Act: -0.1700
Data Index: 1133582 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.7773. Min Act: -0.1700
Data Index: 8384100 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.7773. Min Act: -0.1700
Data Index: 2033985 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.7773. Min Act: -0.1700
Data Index: 7937295 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.7617. Min Act: -0.1700
Data Index: 4812317 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.7929. Min Act: -0.1700
Data Index: 4331791 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.7147. Min Act: -0.1700
Data Index: 1450139 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.7147. Min Act: -0.1700
Data Index: 7761125 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.6991. Min Act: -0.1700
Data Index: 5204660 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.6991. Min Act: -0.1700
Data Index: 3465305 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.6835. Min Act: -0.1700
Data Index: 1242009 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.6991. Min Act: -0.1700
Data Index: 3241507 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.6678. Min Act: -0.1700
Data Index: 306938 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.6991. Min Act: -0.1700
Data Index: 4735056 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.6835. Min Act: -0.1700
Data Index: 7803054 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.6522. Min Act: -0.1700
Data Index: 1310334 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9337. Min Range: -3.9337
Max Act: 3.6522. Min Act: -0.1700
Data Index: 6802366 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19