Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 904 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.5639. Min Act: -0.1700
Data Index: 8523449 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.5154. Min Act: -0.1700
Data Index: 8757152 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.4992. Min Act: -0.1700
Data Index: 4917483 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.4992. Min Act: -0.1700
Data Index: 4917484 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.4668. Min Act: -0.1700
Data Index: 8459895 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.4830. Min Act: -0.1700
Data Index: 2435529 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.4668. Min Act: -0.1700
Data Index: 359400 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.4668. Min Act: -0.1700
Data Index: 4690440 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.4505. Min Act: -0.1700
Data Index: 3661953 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.4668. Min Act: -0.1700
Data Index: 4573994 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.4180. Min Act: -0.1700
Data Index: 469704 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.4180. Min Act: -0.1700
Data Index: 5098406 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.4180. Min Act: -0.1700
Data Index: 8615640 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.4017. Min Act: -0.1700
Data Index: 7479751 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.4017. Min Act: -0.1700
Data Index: 755209 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.4017. Min Act: -0.1700
Data Index: 5245948 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.4017. Min Act: -0.1700
Data Index: 397616 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.4017. Min Act: -0.1700
Data Index: 960030 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.3853. Min Act: -0.1700
Data Index: 4207187 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5639. Min Range: -2.5639
Max Act: 2.4017. Min Act: -0.1700
Data Index: 353392 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19