Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2566 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.6951. Min Act: -0.1700
Data Index: 2643678 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.7263. Min Act: -0.1700
Data Index: 1016368 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.6951. Min Act: -0.1700
Data Index: 7829926 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.6951. Min Act: -0.1700
Data Index: 7131090 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.6951. Min Act: -0.1700
Data Index: 4394800 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.6013. Min Act: -0.1700
Data Index: 6078896 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.6326. Min Act: -0.1700
Data Index: 384760 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.6013. Min Act: -0.1700
Data Index: 4207799 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.6013. Min Act: -0.1700
Data Index: 7271173 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.6013. Min Act: -0.1700
Data Index: 8431478 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.5701. Min Act: -0.1700
Data Index: 2472849 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.5701. Min Act: -0.1700
Data Index: 66232 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.5701. Min Act: -0.1700
Data Index: 353017 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.5076. Min Act: -0.1700
Data Index: 7643051 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.5076. Min Act: -0.1700
Data Index: 8362810 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.5388. Min Act: -0.1700
Data Index: 2987740 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.5701. Min Act: -0.1700
Data Index: 5330504 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.4763. Min Act: -0.1700
Data Index: 2159891 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.4451. Min Act: -0.1700
Data Index: 6930559 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.4451. Min Act: -0.1700
Data Index: 2198972 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19