Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1312. Min Range: -6.1312
Max Act: 6.1312. Min Act: -0.1700
Data Index: 3122160 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1312. Min Range: -6.1312
Max Act: 6.0999. Min Act: -0.1700
Data Index: 835683 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1312. Min Range: -6.1312
Max Act: 6.0687. Min Act: -0.1700
Data Index: 2935918 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1312. Min Range: -6.1312
Max Act: 6.0687. Min Act: -0.1700
Data Index: 5642253 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1312. Min Range: -6.1312
Max Act: 6.0374. Min Act: -0.1700
Data Index: 781171 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1312. Min Range: -6.1312
Max Act: 6.0374. Min Act: -0.1700
Data Index: 7675487 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1312. Min Range: -6.1312
Max Act: 5.9749. Min Act: -0.1700
Data Index: 6716358 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1312. Min Range: -6.1312
Max Act: 6.0062. Min Act: -0.1700
Data Index: 2611434 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1312. Min Range: -6.1312
Max Act: 5.9749. Min Act: -0.1700
Data Index: 2171929 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1312. Min Range: -6.1312
Max Act: 5.9437. Min Act: -0.1700
Data Index: 7452643 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1312. Min Range: -6.1312
Max Act: 5.9437. Min Act: -0.1700
Data Index: 2014819 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1312. Min Range: -6.1312
Max Act: 5.9124. Min Act: -0.1700
Data Index: 4237566 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1312. Min Range: -6.1312
Max Act: 5.9124. Min Act: -0.1700
Data Index: 7310114 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1312. Min Range: -6.1312
Max Act: 5.9124. Min Act: -0.1700
Data Index: 5993760 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1312. Min Range: -6.1312
Max Act: 5.9124. Min Act: -0.1700
Data Index: 7186054 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1312. Min Range: -6.1312
Max Act: 5.8499. Min Act: -0.1700
Data Index: 5475658 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1312. Min Range: -6.1312
Max Act: 5.8812. Min Act: -0.1700
Data Index: 2711790 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1312. Min Range: -6.1312
Max Act: 5.8812. Min Act: -0.1700
Data Index: 6810224 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1312. Min Range: -6.1312
Max Act: 5.8812. Min Act: -0.1700
Data Index: 6970109 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1312. Min Range: -6.1312
Max Act: 5.8499. Min Act: -0.1700
Data Index: 5281530 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19