Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2443 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.8725. Min Act: -0.1700
Data Index: 3339001 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.8382. Min Act: -0.1700
Data Index: 3689650 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.8297. Min Act: -0.1700
Data Index: 3558459 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.8297. Min Act: -0.1700
Data Index: 6053388 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.8211. Min Act: -0.1700
Data Index: 353081 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.8125. Min Act: -0.1700
Data Index: 964886 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.8211. Min Act: -0.1700
Data Index: 5797910 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.8211. Min Act: -0.1700
Data Index: 3967270 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.8125. Min Act: -0.1700
Data Index: 5530624 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.7953. Min Act: -0.1700
Data Index: 964887 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.7867. Min Act: -0.1700
Data Index: 5530625 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.7781. Min Act: -0.1700
Data Index: 6369168 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.7781. Min Act: -0.1700
Data Index: 8344878 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.7867. Min Act: -0.1700
Data Index: 6529231 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.7781. Min Act: -0.1700
Data Index: 5410204 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.7781. Min Act: -0.1700
Data Index: 6002609 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.7867. Min Act: -0.1700
Data Index: 1070610 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.7781. Min Act: -0.1700
Data Index: 5614045 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.7694. Min Act: -0.1700
Data Index: 7004764 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8725. Min Range: -1.8725
Max Act: 1.7781. Min Act: -0.1700
Data Index: 7499251 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19