Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3374 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0143. Min Range: -3.0143
Max Act: 3.0143. Min Act: -0.1700
Data Index: 5469837 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.9827. Min Act: -0.1700
Data Index: 6844453 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.9511. Min Act: -0.1700
Data Index: 7038518 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.9194. Min Act: -0.1700
Data Index: 5753653 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.9352. Min Act: -0.1699
Data Index: 4311902 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.9194. Min Act: -0.1700
Data Index: 2789774 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.9194. Min Act: -0.1700
Data Index: 3596818 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.9035. Min Act: -0.1700
Data Index: 4246240 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.8877. Min Act: -0.1700
Data Index: 2929904 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.8559. Min Act: -0.1700
Data Index: 7755357 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.8877. Min Act: -0.1700
Data Index: 3970739 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.8718. Min Act: -0.1700
Data Index: 6525937 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.8718. Min Act: -0.1700
Data Index: 211335 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.8718. Min Act: -0.1700
Data Index: 5715777 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.8559. Min Act: -0.1700
Data Index: 4179491 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.8718. Min Act: -0.1700
Data Index: 7301177 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.8559. Min Act: -0.1700
Data Index: 5093007 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.8559. Min Act: -0.1700
Data Index: 7795184 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.8718. Min Act: -0.1700
Data Index: 7956304 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0143. Min Range: -3.0143
Max Act: 2.8559. Min Act: -0.1700
Data Index: 8485757 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19