Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2980. Min Range: -6.2980
Max Act: 6.2980. Min Act: -0.1700
Data Index: 5053295 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2980. Min Range: -6.2980
Max Act: 6.2355. Min Act: -0.1700
Data Index: 3301101 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2980. Min Range: -6.2980
Max Act: 6.2355. Min Act: -0.1700
Data Index: 266770 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2980. Min Range: -6.2980
Max Act: 6.2042. Min Act: -0.1700
Data Index: 2682746 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2980. Min Range: -6.2980
Max Act: 6.1417. Min Act: -0.1700
Data Index: 4899806 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2980. Min Range: -6.2980
Max Act: 6.1105. Min Act: -0.1700
Data Index: 6370783 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2980. Min Range: -6.2980
Max Act: 5.9855. Min Act: -0.1700
Data Index: 4926547 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2980. Min Range: -6.2980
Max Act: 6.0167. Min Act: -0.1700
Data Index: 6864834 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2980. Min Range: -6.2980
Max Act: 5.9542. Min Act: -0.1700
Data Index: 860107 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2980. Min Range: -6.2980
Max Act: 5.9230. Min Act: -0.1700
Data Index: 1702202 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2980. Min Range: -6.2980
Max Act: 5.9230. Min Act: -0.1700
Data Index: 1702201 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2980. Min Range: -6.2980
Max Act: 5.9230. Min Act: -0.1700
Data Index: 4359388 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2980. Min Range: -6.2980
Max Act: 5.8917. Min Act: -0.1700
Data Index: 8307310 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2980. Min Range: -6.2980
Max Act: 5.8917. Min Act: -0.1700
Data Index: 3323066 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2980. Min Range: -6.2980
Max Act: 5.8605. Min Act: -0.1700
Data Index: 8094344 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2980. Min Range: -6.2980
Max Act: 5.8292. Min Act: -0.1700
Data Index: 4092922 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2980. Min Range: -6.2980
Max Act: 5.7980. Min Act: -0.1700
Data Index: 890675 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2980. Min Range: -6.2980
Max Act: 5.8292. Min Act: -0.1700
Data Index: 1694862 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2980. Min Range: -6.2980
Max Act: 5.7667. Min Act: -0.1700
Data Index: 5644918 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2980. Min Range: -6.2980
Max Act: 5.7667. Min Act: -0.1700
Data Index: 1031855 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19