Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1908 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.4127. Min Act: -0.1700
Data Index: 1175004 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.3190. Min Act: -0.1700
Data Index: 8731868 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.3190. Min Act: -0.1700
Data Index: 5787079 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.3190. Min Act: -0.1700
Data Index: 5677459 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.3190. Min Act: -0.1700
Data Index: 556134 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.2877. Min Act: -0.1700
Data Index: 3595174 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.2565. Min Act: -0.1700
Data Index: 4568247 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.2565. Min Act: -0.1700
Data Index: 7880901 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.2252. Min Act: -0.1700
Data Index: 3711838 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.2252. Min Act: -0.1700
Data Index: 1414508 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.2252. Min Act: -0.1700
Data Index: 1307677 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.2252. Min Act: -0.1700
Data Index: 3049152 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.1940. Min Act: -0.1700
Data Index: 4154146 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.2252. Min Act: -0.1700
Data Index: 856500 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.1940. Min Act: -0.1700
Data Index: 4761397 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.1940. Min Act: -0.1700
Data Index: 6132301 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.1627. Min Act: -0.1700
Data Index: 3768242 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.1627. Min Act: -0.1700
Data Index: 90912 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.1627. Min Act: -0.1700
Data Index: 3801700 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4127. Min Range: -4.4127
Max Act: 4.1627. Min Act: -0.1700
Data Index: 1411306 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19