Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3534 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1491. Min Range: -7.1491
Max Act: 7.1491. Min Act: -0.1700
Data Index: 6526357 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.8366. Min Act: -0.1700
Data Index: 3995875 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.8053. Min Act: -0.1700
Data Index: 3506831 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.7116. Min Act: -0.1700
Data Index: 4926505 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.6491. Min Act: -0.1700
Data Index: 1456157 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.6803. Min Act: -0.1700
Data Index: 37366 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.5866. Min Act: -0.1700
Data Index: 7572879 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.5553. Min Act: -0.1700
Data Index: 1020180 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.5241. Min Act: -0.1700
Data Index: 5101356 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.5241. Min Act: -0.1700
Data Index: 3949639 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.4928. Min Act: -0.1700
Data Index: 3006043 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.5241. Min Act: -0.1700
Data Index: 3811503 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.4928. Min Act: -0.1700
Data Index: 5732595 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.4303. Min Act: -0.1700
Data Index: 5275621 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.5241. Min Act: -0.1700
Data Index: 7387257 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.4616. Min Act: -0.1700
Data Index: 1040510 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.4928. Min Act: -0.1700
Data Index: 4943453 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.4616. Min Act: -0.1700
Data Index: 7804083 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.4616. Min Act: -0.1700
Data Index: 2909241 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1491. Min Range: -7.1491
Max Act: 6.4303. Min Act: -0.1700
Data Index: 1393609 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19