Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3102 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0650. Min Act: -0.1700
Data Index: 6155347 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9400. Min Act: -0.1700
Data Index: 7251734 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8463. Min Act: -0.1700
Data Index: 4470931 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8463. Min Act: -0.1700
Data Index: 4671057 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.7525. Min Act: -0.1700
Data Index: 547443 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.7838. Min Act: -0.1700
Data Index: 5745616 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.7213. Min Act: -0.1700
Data Index: 6743890 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.6900. Min Act: -0.1700
Data Index: 1815397 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.7213. Min Act: -0.1700
Data Index: 6557429 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.7213. Min Act: -0.1700
Data Index: 2147702 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.7213. Min Act: -0.1700
Data Index: 2890152 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.6900. Min Act: -0.1700
Data Index: 3573769 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.6900. Min Act: -0.1700
Data Index: 1467319 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.6900. Min Act: -0.1700
Data Index: 6144534 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.6900. Min Act: -0.1700
Data Index: 4964200 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.6900. Min Act: -0.1700
Data Index: 7300448 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.6588. Min Act: -0.1700
Data Index: 5004135 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.6588. Min Act: -0.1700
Data Index: 910311 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.6588. Min Act: -0.1700
Data Index: 4923598 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.6588. Min Act: -0.1700
Data Index: 3561903 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19