Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4890 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1607. Min Range: -7.1607
Max Act: 7.1607. Min Act: -0.1700
Data Index: 2615372 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1607. Min Range: -7.1607
Max Act: 7.0982. Min Act: -0.1700
Data Index: 3250049 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1607. Min Range: -7.1607
Max Act: 7.0045. Min Act: -0.1700
Data Index: 3452534 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1607. Min Range: -7.1607
Max Act: 7.0045. Min Act: -0.1700
Data Index: 7014505 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1607. Min Range: -7.1607
Max Act: 6.9420. Min Act: -0.1700
Data Index: 5893410 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1607. Min Range: -7.1607
Max Act: 6.9420. Min Act: -0.1700
Data Index: 8053349 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1607. Min Range: -7.1607
Max Act: 6.8482. Min Act: -0.1700
Data Index: 7775609 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1607. Min Range: -7.1607
Max Act: 6.7545. Min Act: -0.1700
Data Index: 483324 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1607. Min Range: -7.1607
Max Act: 6.7545. Min Act: -0.1700
Data Index: 2110966 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1607. Min Range: -7.1607
Max Act: 6.7232. Min Act: -0.1700
Data Index: 5724167 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1607. Min Range: -7.1607
Max Act: 6.6607. Min Act: -0.1700
Data Index: 757714 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1607. Min Range: -7.1607
Max Act: 6.6607. Min Act: -0.1700
Data Index: 1553815 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1607. Min Range: -7.1607
Max Act: 6.5670. Min Act: -0.1700
Data Index: 1503492 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1607. Min Range: -7.1607
Max Act: 6.5045. Min Act: -0.1700
Data Index: 632877 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1607. Min Range: -7.1607
Max Act: 6.5045. Min Act: -0.1700
Data Index: 8563701 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1607. Min Range: -7.1607
Max Act: 6.4732. Min Act: -0.1700
Data Index: 2199305 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1607. Min Range: -7.1607
Max Act: 6.4420. Min Act: -0.1700
Data Index: 5173533 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1607. Min Range: -7.1607
Max Act: 6.4420. Min Act: -0.1700
Data Index: 3043173 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1607. Min Range: -7.1607
Max Act: 6.4420. Min Act: -0.1700
Data Index: 550484 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1607. Min Range: -7.1607
Max Act: 6.4107. Min Act: -0.1700
Data Index: 4494090 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19