Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2246 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.6311. Min Act: -0.1700
Data Index: 4364762 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.5371. Min Act: -0.1700
Data Index: 103353 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.5371. Min Act: -0.1700
Data Index: 5832516 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.5371. Min Act: -0.1700
Data Index: 3570421 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.5371. Min Act: -0.1700
Data Index: 3518628 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.5058. Min Act: -0.1700
Data Index: 4669807 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.5058. Min Act: -0.1700
Data Index: 7577109 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.5058. Min Act: -0.1700
Data Index: 8240761 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.5058. Min Act: -0.1700
Data Index: 493220 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.5058. Min Act: -0.1700
Data Index: 1243053 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.5058. Min Act: -0.1700
Data Index: 378008 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.4432. Min Act: -0.1700
Data Index: 3659993 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.4745. Min Act: -0.1700
Data Index: 1448284 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.4432. Min Act: -0.1700
Data Index: 415179 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.4745. Min Act: -0.1700
Data Index: 3027394 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.4432. Min Act: -0.1700
Data Index: 2876580 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.4745. Min Act: -0.1699
Data Index: 2220828 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.4745. Min Act: -0.1700
Data Index: 2219118 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.4745. Min Act: -0.1700
Data Index: 1117861 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6311. Min Range: -3.6311
Max Act: 3.4745. Min Act: -0.1700
Data Index: 131902 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19