Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 505 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.5943. Min Act: -0.1700
Data Index: 6860492 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.6256. Min Act: -0.1700
Data Index: 375427 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.5943. Min Act: -0.1700
Data Index: 5635985 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.5631. Min Act: -0.1700
Data Index: 8634259 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.5318. Min Act: -0.1700
Data Index: 5137949 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.4381. Min Act: -0.1700
Data Index: 2156381 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.4381. Min Act: -0.1700
Data Index: 254536 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.4381. Min Act: -0.1700
Data Index: 8270895 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.4068. Min Act: -0.1700
Data Index: 3983290 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.4068. Min Act: -0.1700
Data Index: 4838659 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.3131. Min Act: -0.1700
Data Index: 8545708 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.2818. Min Act: -0.1700
Data Index: 1422789 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.2818. Min Act: -0.1700
Data Index: 5666853 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.2818. Min Act: -0.1700
Data Index: 8000421 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.3131. Min Act: -0.1700
Data Index: 5119464 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.2193. Min Act: -0.1700
Data Index: 4738144 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.2506. Min Act: -0.1700
Data Index: 8228568 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.2506. Min Act: -0.1700
Data Index: 7302101 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.2506. Min Act: -0.1700
Data Index: 5667867 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6256. Min Range: -5.6256
Max Act: 5.2506. Min Act: -0.1700
Data Index: 6396717 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19