Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6382 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.4023. Min Act: -0.1700
Data Index: 2548769 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.3085. Min Act: -0.1700
Data Index: 2151238 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.2460. Min Act: -0.1700
Data Index: 372237 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.1523. Min Act: -0.1700
Data Index: 6917999 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.0898. Min Act: -0.1700
Data Index: 1699105 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.0898. Min Act: -0.1700
Data Index: 8232191 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.0898. Min Act: -0.1700
Data Index: 6807813 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.0273. Min Act: -0.1700
Data Index: 3090450 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.0585. Min Act: -0.1700
Data Index: 2032661 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.0585. Min Act: -0.1700
Data Index: 7335034 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.0273. Min Act: -0.1700
Data Index: 2220134 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.9648. Min Act: -0.1700
Data Index: 6958915 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.9648. Min Act: -0.1700
Data Index: 8086312 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.9023. Min Act: -0.1700
Data Index: 4068194 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.9023. Min Act: -0.1700
Data Index: 8791020 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.9023. Min Act: -0.1700
Data Index: 1786337 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.8710. Min Act: -0.1700
Data Index: 1770791 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.8710. Min Act: -0.1700
Data Index: 2153122 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.9023. Min Act: -0.1700
Data Index: 2571122 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.8398. Min Act: -0.1700
Data Index: 2287162 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19