Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2563 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.5345. Min Act: -0.1700
Data Index: 6514904 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.4408. Min Act: -0.1700
Data Index: 8098912 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.3783. Min Act: -0.1700
Data Index: 7265091 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.3470. Min Act: -0.1700
Data Index: 1613105 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.3158. Min Act: -0.1700
Data Index: 4736514 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.3470. Min Act: -0.1700
Data Index: 6367969 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.3470. Min Act: -0.1700
Data Index: 2851748 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.2845. Min Act: -0.1700
Data Index: 3508778 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.2533. Min Act: -0.1700
Data Index: 1355722 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.2220. Min Act: -0.1700
Data Index: 42085 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.1908. Min Act: -0.1700
Data Index: 7413296 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.1908. Min Act: -0.1700
Data Index: 3163098 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.1908. Min Act: -0.1700
Data Index: 5294871 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.1595. Min Act: -0.1700
Data Index: 5238496 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.1908. Min Act: -0.1700
Data Index: 6625614 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.1595. Min Act: -0.1700
Data Index: 6069690 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.1282. Min Act: -0.1700
Data Index: 3953990 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.1595. Min Act: -0.1700
Data Index: 3456326 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.1282. Min Act: -0.1700
Data Index: 603841 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5345. Min Range: -4.5345
Max Act: 4.1282. Min Act: -0.1700
Data Index: 2640425 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19