Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3918 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2617. Min Range: -6.2617
Max Act: 6.2617. Min Act: -0.1700
Data Index: 7446914 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2617. Min Range: -6.2617
Max Act: 6.1680. Min Act: -0.1700
Data Index: 7446913 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2617. Min Range: -6.2617
Max Act: 6.0742. Min Act: -0.1700
Data Index: 3616327 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.8867. Min Act: -0.1700
Data Index: 5920947 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.8867. Min Act: -0.1700
Data Index: 555677 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.8242. Min Act: -0.1700
Data Index: 4229320 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.8242. Min Act: -0.1700
Data Index: 5605449 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.7930. Min Act: -0.1700
Data Index: 7353843 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.7930. Min Act: -0.1700
Data Index: 748226 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.7617. Min Act: -0.1700
Data Index: 1295969 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.7617. Min Act: -0.1700
Data Index: 1635422 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.7617. Min Act: -0.1700
Data Index: 2348432 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.7617. Min Act: -0.1700
Data Index: 6778750 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.7617. Min Act: -0.1700
Data Index: 8095321 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.7617. Min Act: -0.1700
Data Index: 5214415 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.7617. Min Act: -0.1700
Data Index: 4361010 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.6992. Min Act: -0.1700
Data Index: 7353841 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.6992. Min Act: -0.1700
Data Index: 3956201 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.6992. Min Act: -0.1700
Data Index: 1196656 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.6992. Min Act: -0.1700
Data Index: 7372331 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19