Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2599 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.4309. Min Act: -0.1700
Data Index: 6208428 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.2121. Min Act: -0.1700
Data Index: 1494493 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.1184. Min Act: -0.1700
Data Index: 7023671 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.1496. Min Act: -0.1700
Data Index: 3664045 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.0871. Min Act: -0.1700
Data Index: 6549988 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.0871. Min Act: -0.1700
Data Index: 2864378 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.0246. Min Act: -0.1700
Data Index: 3565676 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.0246. Min Act: -0.1700
Data Index: 199928 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4309. Min Range: -7.4309
Max Act: 7.0246. Min Act: -0.1700
Data Index: 1275599 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.9934. Min Act: -0.1700
Data Index: 669001 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.9621. Min Act: -0.1700
Data Index: 5154316 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.9309. Min Act: -0.1700
Data Index: 2530856 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.9309. Min Act: -0.1700
Data Index: 488860 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.8684. Min Act: -0.1700
Data Index: 46349 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.8996. Min Act: -0.1700
Data Index: 1875444 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.8996. Min Act: -0.1700
Data Index: 2358956 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.8684. Min Act: -0.1700
Data Index: 6701405 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.8684. Min Act: -0.1700
Data Index: 5625727 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.8684. Min Act: -0.1700
Data Index: 1711086 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4309. Min Range: -7.4309
Max Act: 6.8684. Min Act: -0.1700
Data Index: 4303263 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19