Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 558 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.9154. Min Act: -0.1700
Data Index: 7125066 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.8529. Min Act: -0.1700
Data Index: 4812450 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.8529. Min Act: -0.1700
Data Index: 6186531 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.8529. Min Act: -0.1700
Data Index: 727786 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.8529. Min Act: -0.1700
Data Index: 6011008 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.7591. Min Act: -0.1700
Data Index: 7984607 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.6654. Min Act: -0.1700
Data Index: 7797419 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.6654. Min Act: -0.1700
Data Index: 542547 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.5404. Min Act: -0.1700
Data Index: 5048145 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.5716. Min Act: -0.1700
Data Index: 6510407 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.5404. Min Act: -0.1700
Data Index: 6678240 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.4779. Min Act: -0.1700
Data Index: 6567122 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.4779. Min Act: -0.1700
Data Index: 274257 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.4466. Min Act: -0.1700
Data Index: 7361282 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.4779. Min Act: -0.1700
Data Index: 7788869 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.3841. Min Act: -0.1700
Data Index: 8650761 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.4154. Min Act: -0.1700
Data Index: 3942576 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.3841. Min Act: -0.1700
Data Index: 4020051 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.2904. Min Act: -0.1700
Data Index: 887035 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9154. Min Range: -5.9154
Max Act: 5.3216. Min Act: -0.1700
Data Index: 3494108 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19