Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1371 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5489. Min Range: -6.5489
Max Act: 6.5489. Min Act: -0.1700
Data Index: 5572418 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5489. Min Range: -6.5489
Max Act: 6.3927. Min Act: -0.1700
Data Index: 1583540 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5489. Min Range: -6.5489
Max Act: 6.0802. Min Act: -0.1700
Data Index: 4352480 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5489. Min Range: -6.5489
Max Act: 6.0802. Min Act: -0.1700
Data Index: 7819281 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5489. Min Range: -6.5489
Max Act: 6.0802. Min Act: -0.1700
Data Index: 8788728 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5489. Min Range: -6.5489
Max Act: 6.0489. Min Act: -0.1700
Data Index: 4336644 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5489. Min Range: -6.5489
Max Act: 6.0489. Min Act: -0.1700
Data Index: 7599748 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5489. Min Range: -6.5489
Max Act: 6.0489. Min Act: -0.1700
Data Index: 630241 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5489. Min Range: -6.5489
Max Act: 6.0489. Min Act: -0.1700
Data Index: 4070782 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5489. Min Range: -6.5489
Max Act: 6.0177. Min Act: -0.1700
Data Index: 1367774 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5489. Min Range: -6.5489
Max Act: 6.0489. Min Act: -0.1700
Data Index: 1893331 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5489. Min Range: -6.5489
Max Act: 6.0489. Min Act: -0.1700
Data Index: 8788750 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5489. Min Range: -6.5489
Max Act: 5.9864. Min Act: -0.1700
Data Index: 5837792 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5489. Min Range: -6.5489
Max Act: 5.9864. Min Act: -0.1700
Data Index: 2150000 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5489. Min Range: -6.5489
Max Act: 5.9864. Min Act: -0.1700
Data Index: 1543479 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5489. Min Range: -6.5489
Max Act: 5.9552. Min Act: -0.1700
Data Index: 8226198 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5489. Min Range: -6.5489
Max Act: 5.9552. Min Act: -0.1700
Data Index: 6036296 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5489. Min Range: -6.5489
Max Act: 5.9552. Min Act: -0.1700
Data Index: 5169950 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5489. Min Range: -6.5489
Max Act: 5.9239. Min Act: -0.1700
Data Index: 8110453 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5489. Min Range: -6.5489
Max Act: 5.9239. Min Act: -0.1700
Data Index: 6284286 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19