Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4077 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1112. Min Range: -5.1112
Max Act: 5.1112. Min Act: -0.1700
Data Index: 7552850 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1112. Min Range: -5.1112
Max Act: 5.0174. Min Act: -0.1700
Data Index: 5460215 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1112. Min Range: -5.1112
Max Act: 4.9862. Min Act: -0.1700
Data Index: 2573350 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1112. Min Range: -5.1112
Max Act: 4.9237. Min Act: -0.1700
Data Index: 146892 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1112. Min Range: -5.1112
Max Act: 4.8612. Min Act: -0.1700
Data Index: 1708204 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1112. Min Range: -5.1112
Max Act: 4.8924. Min Act: -0.1700
Data Index: 1395781 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1112. Min Range: -5.1112
Max Act: 4.8924. Min Act: -0.1700
Data Index: 173263 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1112. Min Range: -5.1112
Max Act: 4.8612. Min Act: -0.1700
Data Index: 6466069 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1112. Min Range: -5.1112
Max Act: 4.8924. Min Act: -0.1700
Data Index: 1877039 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1112. Min Range: -5.1112
Max Act: 4.8299. Min Act: -0.1700
Data Index: 6447151 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1112. Min Range: -5.1112
Max Act: 4.8612. Min Act: -0.1700
Data Index: 5662171 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1112. Min Range: -5.1112
Max Act: 4.8612. Min Act: -0.1700
Data Index: 4350712 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1112. Min Range: -5.1112
Max Act: 4.7987. Min Act: -0.1700
Data Index: 7884419 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1112. Min Range: -5.1112
Max Act: 4.7987. Min Act: -0.1700
Data Index: 555808 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1112. Min Range: -5.1112
Max Act: 4.7987. Min Act: -0.1700
Data Index: 3092976 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1112. Min Range: -5.1112
Max Act: 4.7674. Min Act: -0.1700
Data Index: 7089550 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1112. Min Range: -5.1112
Max Act: 4.7674. Min Act: -0.1700
Data Index: 2430095 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1112. Min Range: -5.1112
Max Act: 4.7049. Min Act: -0.1700
Data Index: 1027616 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1112. Min Range: -5.1112
Max Act: 4.7049. Min Act: -0.1700
Data Index: 5583772 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1112. Min Range: -5.1112
Max Act: 4.7049. Min Act: -0.1700
Data Index: 7320078 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19