Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4534 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1354. Min Range: -7.1354
Max Act: 7.1354. Min Act: -0.1700
Data Index: 7869534 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.9166. Min Act: -0.1700
Data Index: 7774960 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.8541. Min Act: -0.1700
Data Index: 6930131 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.8229. Min Act: -0.1700
Data Index: 5835010 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.8229. Min Act: -0.1700
Data Index: 6632982 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.7916. Min Act: -0.1700
Data Index: 7009515 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.7291. Min Act: -0.1700
Data Index: 8070653 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.6666. Min Act: -0.1700
Data Index: 3914812 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.6979. Min Act: -0.1700
Data Index: 2181835 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.6979. Min Act: -0.1700
Data Index: 4245688 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.6666. Min Act: -0.1700
Data Index: 1304313 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.6666. Min Act: -0.1700
Data Index: 4837961 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.6354. Min Act: -0.1700
Data Index: 5553100 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.6666. Min Act: -0.1700
Data Index: 2740034 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.6666. Min Act: -0.1700
Data Index: 8519602 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.6354. Min Act: -0.1700
Data Index: 6027874 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.6354. Min Act: -0.1700
Data Index: 232377 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.6041. Min Act: -0.1700
Data Index: 7340014 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.5729. Min Act: -0.1700
Data Index: 4282250 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1354. Min Range: -7.1354
Max Act: 6.5729. Min Act: -0.1700
Data Index: 6664248 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19