Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1586. Min Range: -7.1586
Max Act: 7.1586. Min Act: -0.1700
Data Index: 1685256 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1586. Min Range: -7.1586
Max Act: 7.0961. Min Act: -0.1700
Data Index: 8211117 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1586. Min Range: -7.1586
Max Act: 7.0336. Min Act: -0.1700
Data Index: 7087457 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1586. Min Range: -7.1586
Max Act: 6.9711. Min Act: -0.1700
Data Index: 151541 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1586. Min Range: -7.1586
Max Act: 6.9711. Min Act: -0.1700
Data Index: 1787396 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1586. Min Range: -7.1586
Max Act: 6.9711. Min Act: -0.1700
Data Index: 435476 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1586. Min Range: -7.1586
Max Act: 6.9711. Min Act: -0.1700
Data Index: 5863981 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1586. Min Range: -7.1586
Max Act: 6.9711. Min Act: -0.1700
Data Index: 735892 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1586. Min Range: -7.1586
Max Act: 6.9399. Min Act: -0.1700
Data Index: 855469 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1586. Min Range: -7.1586
Max Act: 6.9086. Min Act: -0.1700
Data Index: 5575644 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1586. Min Range: -7.1586
Max Act: 6.9086. Min Act: -0.1700
Data Index: 4270088 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1586. Min Range: -7.1586
Max Act: 6.9399. Min Act: -0.1700
Data Index: 4032292 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1586. Min Range: -7.1586
Max Act: 6.9086. Min Act: -0.1700
Data Index: 8602135 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1586. Min Range: -7.1586
Max Act: 6.8774. Min Act: -0.1700
Data Index: 51857 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1586. Min Range: -7.1586
Max Act: 6.8774. Min Act: -0.1700
Data Index: 2711171 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1586. Min Range: -7.1586
Max Act: 6.8461. Min Act: -0.1700
Data Index: 4767899 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1586. Min Range: -7.1586
Max Act: 6.8774. Min Act: -0.1700
Data Index: 1994735 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1586. Min Range: -7.1586
Max Act: 6.8774. Min Act: -0.1700
Data Index: 8531589 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1586. Min Range: -7.1586
Max Act: 6.8149. Min Act: -0.1700
Data Index: 3448594 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1586. Min Range: -7.1586
Max Act: 6.8461. Min Act: -0.1700
Data Index: 4604008 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19