Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1152 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.4055. Min Act: -0.1700
Data Index: 8069205 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.3742. Min Act: -0.1700
Data Index: 5592067 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.2805. Min Act: -0.1700
Data Index: 5540985 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.2805. Min Act: -0.1700
Data Index: 8044142 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.2492. Min Act: -0.1700
Data Index: 1125233 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.2805. Min Act: -0.1700
Data Index: 5651694 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.2180. Min Act: -0.1700
Data Index: 223345 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.2492. Min Act: -0.1700
Data Index: 8501428 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.1867. Min Act: -0.1700
Data Index: 6063170 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.1555. Min Act: -0.1700
Data Index: 535089 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.2180. Min Act: -0.1700
Data Index: 6051311 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.1867. Min Act: -0.1700
Data Index: 5509139 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.1867. Min Act: -0.1700
Data Index: 2230826 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.1867. Min Act: -0.1700
Data Index: 4334867 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.1555. Min Act: -0.1700
Data Index: 6031303 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.1867. Min Act: -0.1700
Data Index: 5639863 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.1555. Min Act: -0.1700
Data Index: 339735 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.1555. Min Act: -0.1700
Data Index: 3425994 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.1555. Min Act: -0.1700
Data Index: 7271414 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4055. Min Range: -5.4055
Max Act: 5.1555. Min Act: -0.1700
Data Index: 6435591 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19