Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 972 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3131. Min Range: -5.3131
Max Act: 5.3131. Min Act: -0.1700
Data Index: 5894168 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.8756. Min Act: -0.1700
Data Index: 890436 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.7506. Min Act: -0.1700
Data Index: 5220078 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.7506. Min Act: -0.1700
Data Index: 4789087 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.7193. Min Act: -0.1700
Data Index: 2049110 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.6568. Min Act: -0.1700
Data Index: 5417765 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.6568. Min Act: -0.1700
Data Index: 6915473 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.6256. Min Act: -0.1700
Data Index: 43095 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.6256. Min Act: -0.1700
Data Index: 5363716 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.4693. Min Act: -0.1700
Data Index: 2050881 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.4693. Min Act: -0.1700
Data Index: 3502856 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.4693. Min Act: -0.1700
Data Index: 6588925 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.4693. Min Act: -0.1700
Data Index: 248114 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.4693. Min Act: -0.1700
Data Index: 2996019 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.4381. Min Act: -0.1700
Data Index: 2033040 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.4068. Min Act: -0.1700
Data Index: 2712993 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.5006. Min Act: -0.1700
Data Index: 5882984 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.4381. Min Act: -0.1700
Data Index: 4866618 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.4068. Min Act: -0.1700
Data Index: 2070710 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.4381. Min Act: -0.1700
Data Index: 4878107 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19