Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2815 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.5873. Min Act: -0.1700
Data Index: 4189284 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.4936. Min Act: -0.1700
Data Index: 7235789 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.4936. Min Act: -0.1700
Data Index: 5102672 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.5248. Min Act: -0.1700
Data Index: 5080331 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.4936. Min Act: -0.1700
Data Index: 966114 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.4936. Min Act: -0.1700
Data Index: 4052331 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.4623. Min Act: -0.1700
Data Index: 1925569 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.4623. Min Act: -0.1700
Data Index: 6883063 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.4623. Min Act: -0.1700
Data Index: 4409719 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.4311. Min Act: -0.1700
Data Index: 4320266 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.3998. Min Act: -0.1700
Data Index: 7045395 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.4311. Min Act: -0.1700
Data Index: 5061645 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.4311. Min Act: -0.1700
Data Index: 463088 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.3998. Min Act: -0.1700
Data Index: 5788253 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.4311. Min Act: -0.1700
Data Index: 3865831 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.4311. Min Act: -0.1700
Data Index: 1227713 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.4311. Min Act: -0.1700
Data Index: 5622115 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.4311. Min Act: -0.1700
Data Index: 597988 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.3998. Min Act: -0.1700
Data Index: 1479027 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5873. Min Range: -4.5873
Max Act: 4.4311. Min Act: -0.1700
Data Index: 3923135 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19