Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2272 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2811. Min Range: -5.2811
Max Act: 5.2499. Min Act: -0.1700
Data Index: 7132909 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2811. Min Range: -5.2811
Max Act: 5.2811. Min Act: -0.1700
Data Index: 323111 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2811. Min Range: -5.2811
Max Act: 5.2811. Min Act: -0.1700
Data Index: 2807992 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2811. Min Range: -5.2811
Max Act: 5.1249. Min Act: -0.1700
Data Index: 6783850 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2811. Min Range: -5.2811
Max Act: 5.1249. Min Act: -0.1700
Data Index: 5418524 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2811. Min Range: -5.2811
Max Act: 5.1561. Min Act: -0.1700
Data Index: 7061746 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2811. Min Range: -5.2811
Max Act: 5.1561. Min Act: -0.1700
Data Index: 3347485 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2811. Min Range: -5.2811
Max Act: 5.1249. Min Act: -0.1700
Data Index: 2737778 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2811. Min Range: -5.2811
Max Act: 5.1249. Min Act: -0.1700
Data Index: 2294414 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2811. Min Range: -5.2811
Max Act: 5.1249. Min Act: -0.1700
Data Index: 8751998 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2811. Min Range: -5.2811
Max Act: 5.0936. Min Act: -0.1700
Data Index: 2616923 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2811. Min Range: -5.2811
Max Act: 5.0624. Min Act: -0.1700
Data Index: 7477468 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2811. Min Range: -5.2811
Max Act: 4.9999. Min Act: -0.1700
Data Index: 6035109 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2811. Min Range: -5.2811
Max Act: 4.9686. Min Act: -0.1700
Data Index: 6279837 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2811. Min Range: -5.2811
Max Act: 4.9686. Min Act: -0.1700
Data Index: 4923903 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2811. Min Range: -5.2811
Max Act: 4.9374. Min Act: -0.1700
Data Index: 1883199 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2811. Min Range: -5.2811
Max Act: 4.9686. Min Act: -0.1700
Data Index: 7607718 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2811. Min Range: -5.2811
Max Act: 4.9374. Min Act: -0.1700
Data Index: 6035112 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2811. Min Range: -5.2811
Max Act: 4.9061. Min Act: -0.1700
Data Index: 3655611 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2811. Min Range: -5.2811
Max Act: 4.8749. Min Act: -0.1700
Data Index: 2165327 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19