Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3070 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3802. Min Range: -4.3802
Max Act: 4.3802. Min Act: -0.1700
Data Index: 5020677 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3802. Min Range: -4.3802
Max Act: 4.1301. Min Act: -0.1700
Data Index: 1967343 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3802. Min Range: -4.3802
Max Act: 4.1614. Min Act: -0.1700
Data Index: 6785220 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3802. Min Range: -4.3802
Max Act: 4.0364. Min Act: -0.1700
Data Index: 8805393 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3802. Min Range: -4.3802
Max Act: 4.0989. Min Act: -0.1700
Data Index: 1855639 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3802. Min Range: -4.3802
Max Act: 4.0051. Min Act: -0.1700
Data Index: 2085535 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3802. Min Range: -4.3802
Max Act: 3.9738. Min Act: -0.1700
Data Index: 4965161 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3802. Min Range: -4.3802
Max Act: 4.0051. Min Act: -0.1700
Data Index: 4029182 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3802. Min Range: -4.3802
Max Act: 4.0051. Min Act: -0.1700
Data Index: 4004444 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3802. Min Range: -4.3802
Max Act: 4.0051. Min Act: -0.1700
Data Index: 6962339 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3802. Min Range: -4.3802
Max Act: 4.0051. Min Act: -0.1700
Data Index: 2290657 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3802. Min Range: -4.3802
Max Act: 3.9738. Min Act: -0.1700
Data Index: 5222020 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3802. Min Range: -4.3802
Max Act: 4.0051. Min Act: -0.1700
Data Index: 3826546 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3802. Min Range: -4.3802
Max Act: 4.0051. Min Act: -0.1700
Data Index: 5467998 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3802. Min Range: -4.3802
Max Act: 4.0051. Min Act: -0.1700
Data Index: 1631915 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3802. Min Range: -4.3802
Max Act: 3.9426. Min Act: -0.1700
Data Index: 3297924 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3802. Min Range: -4.3802
Max Act: 3.9738. Min Act: -0.1700
Data Index: 6309987 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3802. Min Range: -4.3802
Max Act: 3.9738. Min Act: -0.1700
Data Index: 1384043 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3802. Min Range: -4.3802
Max Act: 3.9738. Min Act: -0.1700
Data Index: 7669875 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3802. Min Range: -4.3802
Max Act: 3.9738. Min Act: -0.1700
Data Index: 4629055 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19