Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1442 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0385. Min Range: -9.0385
Max Act: 9.0385. Min Act: -0.1700
Data Index: 1630687 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.9447. Min Act: -0.1700
Data Index: 6707321 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.8510. Min Act: -0.1700
Data Index: 1471874 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.8822. Min Act: -0.1700
Data Index: 4182945 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.8510. Min Act: -0.1700
Data Index: 5594834 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.8197. Min Act: -0.1700
Data Index: 6276756 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.7572. Min Act: -0.1700
Data Index: 4117604 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.7572. Min Act: -0.1700
Data Index: 6176407 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.7572. Min Act: -0.1700
Data Index: 1517883 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.7572. Min Act: -0.1700
Data Index: 8796394 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.7260. Min Act: -0.1700
Data Index: 8280301 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.7260. Min Act: -0.1700
Data Index: 2306599 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.6947. Min Act: -0.1700
Data Index: 5184435 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.6322. Min Act: -0.1700
Data Index: 4554545 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.5385. Min Act: -0.1700
Data Index: 4231943 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.5385. Min Act: -0.1700
Data Index: 502114 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.5072. Min Act: -0.1700
Data Index: 1793190 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.5072. Min Act: -0.1700
Data Index: 3240586 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.5385. Min Act: -0.1700
Data Index: 6922290 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0385. Min Range: -9.0385
Max Act: 7.5385. Min Act: -0.1700
Data Index: 4249624 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19