Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1445 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2676. Min Range: -7.2676
Max Act: 7.2676. Min Act: -0.1700
Data Index: 3065734 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2676. Min Range: -7.2676
Max Act: 7.2364. Min Act: -0.1700
Data Index: 7176014 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2676. Min Range: -7.2676
Max Act: 7.0801. Min Act: -0.1700
Data Index: 1860447 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2676. Min Range: -7.2676
Max Act: 7.0489. Min Act: -0.1700
Data Index: 2389694 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2676. Min Range: -7.2676
Max Act: 7.0176. Min Act: -0.1700
Data Index: 5276104 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2676. Min Range: -7.2676
Max Act: 7.0176. Min Act: -0.1700
Data Index: 7303947 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2676. Min Range: -7.2676
Max Act: 7.0176. Min Act: -0.1700
Data Index: 8116899 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2676. Min Range: -7.2676
Max Act: 6.9864. Min Act: -0.1700
Data Index: 89381 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2676. Min Range: -7.2676
Max Act: 7.0176. Min Act: -0.1700
Data Index: 1602163 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2676. Min Range: -7.2676
Max Act: 6.9864. Min Act: -0.1700
Data Index: 4523133 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2676. Min Range: -7.2676
Max Act: 6.9551. Min Act: -0.1700
Data Index: 1668616 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2676. Min Range: -7.2676
Max Act: 6.9551. Min Act: -0.1700
Data Index: 1233636 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2676. Min Range: -7.2676
Max Act: 6.9864. Min Act: -0.1700
Data Index: 1709788 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2676. Min Range: -7.2676
Max Act: 6.8614. Min Act: -0.1700
Data Index: 2313168 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2676. Min Range: -7.2676
Max Act: 6.8926. Min Act: -0.1700
Data Index: 7459282 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2676. Min Range: -7.2676
Max Act: 6.8926. Min Act: -0.1700
Data Index: 272606 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2676. Min Range: -7.2676
Max Act: 6.8301. Min Act: -0.1700
Data Index: 113633 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2676. Min Range: -7.2676
Max Act: 6.8301. Min Act: -0.1700
Data Index: 1040791 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2676. Min Range: -7.2676
Max Act: 6.8614. Min Act: -0.1700
Data Index: 7438642 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2676. Min Range: -7.2676
Max Act: 6.8614. Min Act: -0.1700
Data Index: 1896888 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19