Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5291 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3852. Min Range: -8.3852
Max Act: 8.3852. Min Act: -0.1700
Data Index: 1016130 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3852. Min Range: -8.3852
Max Act: 8.1352. Min Act: -0.1700
Data Index: 7820884 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3852. Min Range: -8.3852
Max Act: 8.0727. Min Act: -0.1700
Data Index: 3327025 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3852. Min Range: -8.3852
Max Act: 8.0102. Min Act: -0.1699
Data Index: 1394538 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3852. Min Range: -8.3852
Max Act: 8.0102. Min Act: -0.1700
Data Index: 4805679 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3852. Min Range: -8.3852
Max Act: 7.9477. Min Act: -0.1700
Data Index: 721399 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3852. Min Range: -8.3852
Max Act: 7.9477. Min Act: -0.1700
Data Index: 8143930 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3852. Min Range: -8.3852
Max Act: 7.9477. Min Act: -0.1700
Data Index: 2882488 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3852. Min Range: -8.3852
Max Act: 7.8852. Min Act: -0.1700
Data Index: 2850784 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3852. Min Range: -8.3852
Max Act: 7.8227. Min Act: -0.1700
Data Index: 1051426 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3852. Min Range: -8.3852
Max Act: 7.8227. Min Act: -0.1700
Data Index: 6394905 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3852. Min Range: -8.3852
Max Act: 7.8227. Min Act: -0.1700
Data Index: 6310953 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3852. Min Range: -8.3852
Max Act: 7.7602. Min Act: -0.1700
Data Index: 5486382 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3852. Min Range: -8.3852
Max Act: 7.7602. Min Act: -0.1700
Data Index: 4606631 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3852. Min Range: -8.3852
Max Act: 7.6352. Min Act: -0.1700
Data Index: 1110897 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3852. Min Range: -8.3852
Max Act: 7.6977. Min Act: -0.1700
Data Index: 8069517 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3852. Min Range: -8.3852
Max Act: 7.6352. Min Act: -0.1700
Data Index: 2930533 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3852. Min Range: -8.3852
Max Act: 7.7602. Min Act: -0.1700
Data Index: 1636511 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3852. Min Range: -8.3852
Max Act: 7.6977. Min Act: -0.1700
Data Index: 7474637 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3852. Min Range: -8.3852
Max Act: 7.6977. Min Act: -0.1700
Data Index: 912080 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19