Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3754 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.4097. Min Act: -0.1700
Data Index: 7148454 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.3472. Min Act: -0.1700
Data Index: 2838141 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.2534. Min Act: -0.1700
Data Index: 935969 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.2534. Min Act: -0.1700
Data Index: 3962724 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.2222. Min Act: -0.1700
Data Index: 6893812 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.1284. Min Act: -0.1700
Data Index: 2095817 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.1597. Min Act: -0.1700
Data Index: 4222360 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.1597. Min Act: -0.1700
Data Index: 346498 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.0972. Min Act: -0.1700
Data Index: 2768019 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.0972. Min Act: -0.1700
Data Index: 7231416 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.0972. Min Act: -0.1700
Data Index: 621928 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.0972. Min Act: -0.1700
Data Index: 1690186 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.0972. Min Act: -0.1700
Data Index: 8776500 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.0659. Min Act: -0.1700
Data Index: 2837718 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.0347. Min Act: -0.1700
Data Index: 8119209 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.0347. Min Act: -0.1700
Data Index: 551340 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.0347. Min Act: -0.1700
Data Index: 212133 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4097. Min Range: -7.4097
Max Act: 6.9722. Min Act: -0.1700
Data Index: 2708065 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.0034. Min Act: -0.1700
Data Index: 7923851 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4097. Min Range: -7.4097
Max Act: 7.0034. Min Act: -0.1700
Data Index: 8711366 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19