Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2617 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2999. Min Range: -5.2999
Max Act: 5.2999. Min Act: -0.1700
Data Index: 5148157 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2999. Min Range: -5.2999
Max Act: 5.0187. Min Act: -0.1700
Data Index: 33831 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2999. Min Range: -5.2999
Max Act: 4.9874. Min Act: -0.1700
Data Index: 5650762 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2999. Min Range: -5.2999
Max Act: 4.9562. Min Act: -0.1700
Data Index: 5524894 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2999. Min Range: -5.2999
Max Act: 4.8937. Min Act: -0.1700
Data Index: 1515088 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2999. Min Range: -5.2999
Max Act: 4.8312. Min Act: -0.1700
Data Index: 6826009 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2999. Min Range: -5.2999
Max Act: 4.8312. Min Act: -0.1700
Data Index: 7896985 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2999. Min Range: -5.2999
Max Act: 4.8312. Min Act: -0.1700
Data Index: 7743929 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2999. Min Range: -5.2999
Max Act: 4.7999. Min Act: -0.1700
Data Index: 2609411 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2999. Min Range: -5.2999
Max Act: 4.7687. Min Act: -0.1700
Data Index: 4446012 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2999. Min Range: -5.2999
Max Act: 4.7687. Min Act: -0.1700
Data Index: 1578345 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2999. Min Range: -5.2999
Max Act: 4.7374. Min Act: -0.1700
Data Index: 7345222 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2999. Min Range: -5.2999
Max Act: 4.7374. Min Act: -0.1700
Data Index: 2457955 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2999. Min Range: -5.2999
Max Act: 4.7374. Min Act: -0.1700
Data Index: 3150251 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2999. Min Range: -5.2999
Max Act: 4.7062. Min Act: -0.1700
Data Index: 2118288 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2999. Min Range: -5.2999
Max Act: 4.7687. Min Act: -0.1700
Data Index: 883522 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2999. Min Range: -5.2999
Max Act: 4.7374. Min Act: -0.1700
Data Index: 5052545 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2999. Min Range: -5.2999
Max Act: 4.7374. Min Act: -0.1700
Data Index: 5919773 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2999. Min Range: -5.2999
Max Act: 4.7374. Min Act: -0.1700
Data Index: 8213502 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2999. Min Range: -5.2999
Max Act: 4.7062. Min Act: -0.1700
Data Index: 6781877 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19