Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1976 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.5717. Min Act: -0.1700
Data Index: 2922410 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.4934. Min Act: -0.1700
Data Index: 748188 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.4777. Min Act: -0.1700
Data Index: 4714376 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.4620. Min Act: -0.1700
Data Index: 2122020 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.4307. Min Act: -0.1700
Data Index: 3838026 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.4150. Min Act: -0.1700
Data Index: 2120577 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.4307. Min Act: -0.1700
Data Index: 1587176 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.4150. Min Act: -0.1700
Data Index: 1040979 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.3993. Min Act: -0.1700
Data Index: 3778838 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.3837. Min Act: -0.1700
Data Index: 5839815 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.3680. Min Act: -0.1700
Data Index: 3786869 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.3993. Min Act: -0.1700
Data Index: 4331529 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.4150. Min Act: -0.1700
Data Index: 8074348 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.3837. Min Act: -0.1700
Data Index: 352424 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.3993. Min Act: -0.1700
Data Index: 7662753 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.3993. Min Act: -0.1700
Data Index: 1951566 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.3993. Min Act: -0.1700
Data Index: 2440730 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.3837. Min Act: -0.1700
Data Index: 2575674 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.3837. Min Act: -0.1700
Data Index: 7494082 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5717. Min Range: -3.5717
Max Act: 3.3837. Min Act: -0.1700
Data Index: 89843 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19