Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1169 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1141. Min Range: -3.1141
Max Act: 3.1141. Min Act: -0.1700
Data Index: 2411229 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1141. Min Range: -3.1141
Max Act: 3.0668. Min Act: -0.1700
Data Index: 4234261 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1141. Min Range: -3.1141
Max Act: 3.0668. Min Act: -0.1700
Data Index: 7892964 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1141. Min Range: -3.1141
Max Act: 3.0195. Min Act: -0.1700
Data Index: 82929 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1141. Min Range: -3.1141
Max Act: 3.0195. Min Act: -0.1700
Data Index: 2851801 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1141. Min Range: -3.1141
Max Act: 2.9720. Min Act: -0.1700
Data Index: 3492774 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1141. Min Range: -3.1141
Max Act: 2.9879. Min Act: -0.1700
Data Index: 6371516 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1141. Min Range: -3.1141
Max Act: 3.0195. Min Act: -0.1700
Data Index: 5031852 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1141. Min Range: -3.1141
Max Act: 2.9720. Min Act: -0.1700
Data Index: 389339 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1141. Min Range: -3.1141
Max Act: 2.9720. Min Act: -0.1700
Data Index: 4140793 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1141. Min Range: -3.1141
Max Act: 2.9720. Min Act: -0.1700
Data Index: 4320752 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1141. Min Range: -3.1141
Max Act: 2.9720. Min Act: -0.1700
Data Index: 6650612 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1141. Min Range: -3.1141
Max Act: 2.9720. Min Act: -0.1700
Data Index: 8550812 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1141. Min Range: -3.1141
Max Act: 2.9720. Min Act: -0.1700
Data Index: 2968301 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1141. Min Range: -3.1141
Max Act: 2.9087. Min Act: -0.1700
Data Index: 6520512 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1141. Min Range: -3.1141
Max Act: 2.9246. Min Act: -0.1700
Data Index: 7453023 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1141. Min Range: -3.1141
Max Act: 2.9087. Min Act: -0.1700
Data Index: 2138314 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1141. Min Range: -3.1141
Max Act: 2.9246. Min Act: -0.1700
Data Index: 5212964 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1141. Min Range: -3.1141
Max Act: 2.9246. Min Act: -0.1700
Data Index: 3427930 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1141. Min Range: -3.1141
Max Act: 2.9404. Min Act: -0.1700
Data Index: 1932077 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19