Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1114 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5557. Min Range: -11.5557
Max Act: 11.5557. Min Act: -0.1700
Data Index: 1115953 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5557. Min Range: -11.5557
Max Act: 11.1807. Min Act: -0.1700
Data Index: 3131560 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5557. Min Range: -11.5557
Max Act: 11.1182. Min Act: -0.1700
Data Index: 2800623 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5557. Min Range: -11.5557
Max Act: 11.1182. Min Act: -0.1700
Data Index: 1009264 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5557. Min Range: -11.5557
Max Act: 11.0557. Min Act: -0.1700
Data Index: 8702111 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5557. Min Range: -11.5557
Max Act: 11.0557. Min Act: -0.1700
Data Index: 561079 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5557. Min Range: -11.5557
Max Act: 10.9307. Min Act: -0.1700
Data Index: 4958430 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5557. Min Range: -11.5557
Max Act: 10.8682. Min Act: -0.1700
Data Index: 6327151 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5557. Min Range: -11.5557
Max Act: 10.9307. Min Act: -0.1700
Data Index: 1398540 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5557. Min Range: -11.5557
Max Act: 10.7432. Min Act: -0.1700
Data Index: 315678 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5557. Min Range: -11.5557
Max Act: 10.8057. Min Act: -0.1700
Data Index: 5753827 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5557. Min Range: -11.5557
Max Act: 10.8057. Min Act: -0.1700
Data Index: 2563685 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5557. Min Range: -11.5557
Max Act: 10.6807. Min Act: -0.1700
Data Index: 8702112 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5557. Min Range: -11.5557
Max Act: 10.6807. Min Act: -0.1700
Data Index: 8235211 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5557. Min Range: -11.5557
Max Act: 10.7432. Min Act: -0.1700
Data Index: 633465 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5557. Min Range: -11.5557
Max Act: 10.7432. Min Act: -0.1700
Data Index: 7003553 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5557. Min Range: -11.5557
Max Act: 10.6807. Min Act: -0.1700
Data Index: 6209042 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5557. Min Range: -11.5557
Max Act: 10.6807. Min Act: -0.1700
Data Index: 7944662 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5557. Min Range: -11.5557
Max Act: 10.6807. Min Act: -0.1700
Data Index: 3867108 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5557. Min Range: -11.5557
Max Act: 10.5557. Min Act: -0.1700
Data Index: 8106212 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19