Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2775 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.9803. Min Act: -0.1700
Data Index: 8586516 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.9178. Min Act: -0.1700
Data Index: 7443762 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.9803. Min Act: -0.1700
Data Index: 8123677 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.8553. Min Act: -0.1700
Data Index: 8122554 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.8553. Min Act: -0.1700
Data Index: 3011614 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.8553. Min Act: -0.1700
Data Index: 7484822 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.8865. Min Act: -0.1700
Data Index: 7076361 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.8553. Min Act: -0.1700
Data Index: 586500 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.8553. Min Act: -0.1700
Data Index: 8159998 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.8240. Min Act: -0.1700
Data Index: 6059978 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.8553. Min Act: -0.1700
Data Index: 6330780 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.8240. Min Act: -0.1700
Data Index: 8612882 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.8240. Min Act: -0.1700
Data Index: 5030257 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.7927. Min Act: -0.1700
Data Index: 549015 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.8553. Min Act: -0.1700
Data Index: 7859243 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.8240. Min Act: -0.1700
Data Index: 4122878 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.8240. Min Act: -0.1700
Data Index: 6347905 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.7927. Min Act: -0.1700
Data Index: 6760545 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.7927. Min Act: -0.1700
Data Index: 1356306 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9803. Min Range: -3.9803
Max Act: 3.7927. Min Act: -0.1700
Data Index: 3043126 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19