Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 437 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1435. Min Range: -7.1435
Max Act: 7.1122. Min Act: -0.1700
Data Index: 6812001 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1435. Min Range: -7.1435
Max Act: 7.1435. Min Act: -0.1700
Data Index: 5099951 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1435. Min Range: -7.1435
Max Act: 6.9560. Min Act: -0.1700
Data Index: 5508074 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1435. Min Range: -7.1435
Max Act: 6.9247. Min Act: -0.1700
Data Index: 3433565 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1435. Min Range: -7.1435
Max Act: 6.8622. Min Act: -0.1700
Data Index: 8744651 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1435. Min Range: -7.1435
Max Act: 6.8935. Min Act: -0.1700
Data Index: 5153104 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1435. Min Range: -7.1435
Max Act: 6.8935. Min Act: -0.1700
Data Index: 115859 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1435. Min Range: -7.1435
Max Act: 6.8935. Min Act: -0.1700
Data Index: 712319 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1435. Min Range: -7.1435
Max Act: 6.8622. Min Act: -0.1700
Data Index: 8786696 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1435. Min Range: -7.1435
Max Act: 6.8310. Min Act: -0.1700
Data Index: 3763677 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1435. Min Range: -7.1435
Max Act: 6.7685. Min Act: -0.1700
Data Index: 8622925 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1435. Min Range: -7.1435
Max Act: 6.7685. Min Act: -0.1700
Data Index: 7776297 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1435. Min Range: -7.1435
Max Act: 6.7372. Min Act: -0.1700
Data Index: 4007164 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1435. Min Range: -7.1435
Max Act: 6.7685. Min Act: -0.1700
Data Index: 7680760 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1435. Min Range: -7.1435
Max Act: 6.7060. Min Act: -0.1700
Data Index: 4159720 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1435. Min Range: -7.1435
Max Act: 6.7060. Min Act: -0.1700
Data Index: 2007387 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1435. Min Range: -7.1435
Max Act: 6.6747. Min Act: -0.1700
Data Index: 7523333 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1435. Min Range: -7.1435
Max Act: 6.6435. Min Act: -0.1700
Data Index: 42016 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1435. Min Range: -7.1435
Max Act: 6.6747. Min Act: -0.1700
Data Index: 3967115 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1435. Min Range: -7.1435
Max Act: 6.6747. Min Act: -0.1700
Data Index: 846985 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19