Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 708 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.7124. Min Range: -10.7124
Max Act: 10.7124. Min Act: -0.1700
Data Index: 3472944 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7124. Min Range: -10.7124
Max Act: 10.5874. Min Act: -0.1700
Data Index: 6257124 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7124. Min Range: -10.7124
Max Act: 10.5249. Min Act: -0.1700
Data Index: 429061 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7124. Min Range: -10.7124
Max Act: 10.2124. Min Act: -0.1700
Data Index: 3227426 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7124. Min Range: -10.7124
Max Act: 10.0874. Min Act: -0.1700
Data Index: 2207197 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7124. Min Range: -10.7124
Max Act: 10.0874. Min Act: -0.1700
Data Index: 156859 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7124. Min Range: -10.7124
Max Act: 9.9624. Min Act: -0.1700
Data Index: 3187129 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7124. Min Range: -10.7124
Max Act: 9.9624. Min Act: -0.1700
Data Index: 7589899 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7124. Min Range: -10.7124
Max Act: 9.9624. Min Act: -0.1700
Data Index: 4688710 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7124. Min Range: -10.7124
Max Act: 9.9624. Min Act: -0.1700
Data Index: 7631527 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7124. Min Range: -10.7124
Max Act: 9.9624. Min Act: -0.1700
Data Index: 4411009 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7124. Min Range: -10.7124
Max Act: 9.9624. Min Act: -0.1700
Data Index: 3112171 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7124. Min Range: -10.7124
Max Act: 9.8374. Min Act: -0.1700
Data Index: 3691660 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7124. Min Range: -10.7124
Max Act: 9.8374. Min Act: -0.1700
Data Index: 6974452 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7124. Min Range: -10.7124
Max Act: 9.7749. Min Act: -0.1700
Data Index: 8454607 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7124. Min Range: -10.7124
Max Act: 9.8374. Min Act: -0.1700
Data Index: 3546081 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7124. Min Range: -10.7124
Max Act: 9.8374. Min Act: -0.1700
Data Index: 2859157 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7124. Min Range: -10.7124
Max Act: 9.8374. Min Act: -0.1700
Data Index: 6656974 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7124. Min Range: -10.7124
Max Act: 9.8374. Min Act: -0.1700
Data Index: 7687024 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7124. Min Range: -10.7124
Max Act: 9.7749. Min Act: -0.1700
Data Index: 2202530 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19