Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5680. Min Range: -6.5680
Max Act: 6.5680. Min Act: -0.1700
Data Index: 439545 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5680. Min Range: -6.5680
Max Act: 6.4742. Min Act: -0.1700
Data Index: 8523543 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5680. Min Range: -6.5680
Max Act: 6.1617. Min Act: -0.1700
Data Index: 1187326 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5680. Min Range: -6.5680
Max Act: 6.1305. Min Act: -0.1700
Data Index: 5860061 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5680. Min Range: -6.5680
Max Act: 6.0992. Min Act: -0.1700
Data Index: 3216366 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5680. Min Range: -6.5680
Max Act: 6.0055. Min Act: -0.1700
Data Index: 8195577 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5680. Min Range: -6.5680
Max Act: 5.9742. Min Act: -0.1700
Data Index: 5298547 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5680. Min Range: -6.5680
Max Act: 6.0055. Min Act: -0.1700
Data Index: 7386822 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5680. Min Range: -6.5680
Max Act: 5.9742. Min Act: -0.1700
Data Index: 6433914 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5680. Min Range: -6.5680
Max Act: 5.9742. Min Act: -0.1700
Data Index: 6544544 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5680. Min Range: -6.5680
Max Act: 5.9430. Min Act: -0.1700
Data Index: 7065671 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5680. Min Range: -6.5680
Max Act: 5.9430. Min Act: -0.1700
Data Index: 4567399 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5680. Min Range: -6.5680
Max Act: 5.8805. Min Act: -0.1700
Data Index: 8771611 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5680. Min Range: -6.5680
Max Act: 5.9117. Min Act: -0.1700
Data Index: 630483 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5680. Min Range: -6.5680
Max Act: 5.9117. Min Act: -0.1700
Data Index: 133179 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5680. Min Range: -6.5680
Max Act: 5.9117. Min Act: -0.1700
Data Index: 6739674 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5680. Min Range: -6.5680
Max Act: 5.8805. Min Act: -0.1700
Data Index: 5481900 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5680. Min Range: -6.5680
Max Act: 5.9117. Min Act: -0.1700
Data Index: 2392257 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5680. Min Range: -6.5680
Max Act: 5.8805. Min Act: -0.1700
Data Index: 524139 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5680. Min Range: -6.5680
Max Act: 5.8492. Min Act: -0.1700
Data Index: 2577758 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19