Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3835 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.8050. Min Act: -0.1700
Data Index: 6896429 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.6319. Min Act: -0.1700
Data Index: 2317254 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.6406. Min Act: -0.1700
Data Index: 8031877 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.6057. Min Act: -0.1700
Data Index: 2915413 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.6231. Min Act: -0.1700
Data Index: 5890802 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.6057. Min Act: -0.1700
Data Index: 1483920 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.6144. Min Act: -0.1700
Data Index: 3487944 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.6144. Min Act: -0.1700
Data Index: 5101696 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.5970. Min Act: -0.1699
Data Index: 475857 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.6057. Min Act: -0.1700
Data Index: 3060413 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.5620. Min Act: -0.1700
Data Index: 8167639 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.5269. Min Act: -0.1700
Data Index: 7665496 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.5182. Min Act: -0.1700
Data Index: 1625715 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.5182. Min Act: -0.1700
Data Index: 8292017 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.5182. Min Act: -0.1700
Data Index: 2789703 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.5094. Min Act: -0.1700
Data Index: 5848912 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.5094. Min Act: -0.1700
Data Index: 2899671 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.5006. Min Act: -0.1700
Data Index: 9645 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.5006. Min Act: -0.1700
Data Index: 8174878 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8050. Min Range: -1.8050
Max Act: 1.4831. Min Act: -0.1700
Data Index: 4412384 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19