Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6191 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3855. Min Range: -6.3855
Max Act: 6.3855. Min Act: -0.1700
Data Index: 973985 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3855. Min Range: -6.3855
Max Act: 6.3542. Min Act: -0.1700
Data Index: 3426234 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3855. Min Range: -6.3855
Max Act: 6.2605. Min Act: -0.1700
Data Index: 2002557 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3855. Min Range: -6.3855
Max Act: 6.2605. Min Act: -0.1700
Data Index: 6050637 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3855. Min Range: -6.3855
Max Act: 6.2292. Min Act: -0.1700
Data Index: 1794132 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3855. Min Range: -6.3855
Max Act: 6.1980. Min Act: -0.1700
Data Index: 6598069 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3855. Min Range: -6.3855
Max Act: 6.1980. Min Act: -0.1700
Data Index: 1464092 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3855. Min Range: -6.3855
Max Act: 6.1355. Min Act: -0.1700
Data Index: 3304428 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3855. Min Range: -6.3855
Max Act: 6.1667. Min Act: -0.1700
Data Index: 3305923 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3855. Min Range: -6.3855
Max Act: 6.1355. Min Act: -0.1700
Data Index: 8284608 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3855. Min Range: -6.3855
Max Act: 6.1042. Min Act: -0.1700
Data Index: 7138914 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3855. Min Range: -6.3855
Max Act: 6.0730. Min Act: -0.1700
Data Index: 7565967 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3855. Min Range: -6.3855
Max Act: 6.0105. Min Act: -0.1700
Data Index: 5369023 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3855. Min Range: -6.3855
Max Act: 6.0417. Min Act: -0.1700
Data Index: 5941834 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3855. Min Range: -6.3855
Max Act: 6.0417. Min Act: -0.1700
Data Index: 1344674 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3855. Min Range: -6.3855
Max Act: 6.0105. Min Act: -0.1700
Data Index: 8138437 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3855. Min Range: -6.3855
Max Act: 5.9792. Min Act: -0.1700
Data Index: 131804 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3855. Min Range: -6.3855
Max Act: 6.0105. Min Act: -0.1700
Data Index: 1939912 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3855. Min Range: -6.3855
Max Act: 5.9792. Min Act: -0.1700
Data Index: 4610684 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3855. Min Range: -6.3855
Max Act: 6.0105. Min Act: -0.1700
Data Index: 2754745 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19