Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2878 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.8835. Min Act: -0.1700
Data Index: 6061109 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.8522. Min Act: -0.1699
Data Index: 5971852 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.8522. Min Act: -0.1700
Data Index: 6495766 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.8210. Min Act: -0.1700
Data Index: 1278192 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.8210. Min Act: -0.1700
Data Index: 2929762 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.8210. Min Act: -0.1700
Data Index: 4159614 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.7897. Min Act: -0.1700
Data Index: 8120448 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.7897. Min Act: -0.1700
Data Index: 30674 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.6960. Min Act: -0.1700
Data Index: 4575661 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.7272. Min Act: -0.1686
Data Index: 2327710 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.6960. Min Act: -0.1700
Data Index: 2508682 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.6960. Min Act: -0.1700
Data Index: 2258621 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.6960. Min Act: -0.1700
Data Index: 1166780 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.6647. Min Act: -0.1700
Data Index: 655704 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.6647. Min Act: -0.1699
Data Index: 8344328 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.6647. Min Act: -0.1700
Data Index: 8336828 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.6647. Min Act: -0.1700
Data Index: 6730765 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.6647. Min Act: -0.1700
Data Index: 550033 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.6647. Min Act: -0.1700
Data Index: 2448841 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8835. Min Range: -5.8835
Max Act: 5.6647. Min Act: -0.1700
Data Index: 5404034 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19