Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 342 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.8974. Min Act: -0.1700
Data Index: 8347029 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.8974. Min Act: -0.1700
Data Index: 7484220 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.8662. Min Act: -0.1700
Data Index: 3813302 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.8349. Min Act: -0.1700
Data Index: 5943401 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.8037. Min Act: -0.1700
Data Index: 5585590 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.7724. Min Act: -0.1700
Data Index: 1658649 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.7724. Min Act: -0.1700
Data Index: 6042615 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.7724. Min Act: -0.1700
Data Index: 878192 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.7724. Min Act: -0.1700
Data Index: 8799892 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.7412. Min Act: -0.1700
Data Index: 7149485 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.7412. Min Act: -0.1700
Data Index: 232476 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.7412. Min Act: -0.1699
Data Index: 830714 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.7099. Min Act: -0.1700
Data Index: 6577928 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.7412. Min Act: -0.1700
Data Index: 7308268 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.6787. Min Act: -0.1700
Data Index: 8450156 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.6787. Min Act: -0.1700
Data Index: 6184793 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.6787. Min Act: -0.1700
Data Index: 2054798 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.7099. Min Act: -0.1700
Data Index: 2943194 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.6474. Min Act: -0.1700
Data Index: 5567945 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8974. Min Range: -5.8974
Max Act: 5.6787. Min Act: -0.1700
Data Index: 939964 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19