Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4267 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0648. Min Range: -6.0648
Max Act: 6.0648. Min Act: -0.1700
Data Index: 6385912 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0648. Min Range: -6.0648
Max Act: 6.0335. Min Act: -0.1700
Data Index: 2613526 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0648. Min Range: -6.0648
Max Act: 5.8148. Min Act: -0.1700
Data Index: 8559721 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0648. Min Range: -6.0648
Max Act: 5.8148. Min Act: -0.1700
Data Index: 5755658 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0648. Min Range: -6.0648
Max Act: 5.8148. Min Act: -0.1700
Data Index: 5160860 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0648. Min Range: -6.0648
Max Act: 5.8148. Min Act: -0.1700
Data Index: 5873455 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0648. Min Range: -6.0648
Max Act: 5.7523. Min Act: -0.1700
Data Index: 3492567 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0648. Min Range: -6.0648
Max Act: 5.7523. Min Act: -0.1700
Data Index: 676353 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0648. Min Range: -6.0648
Max Act: 5.7523. Min Act: -0.1700
Data Index: 6034342 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0648. Min Range: -6.0648
Max Act: 5.7210. Min Act: -0.1700
Data Index: 1445540 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0648. Min Range: -6.0648
Max Act: 5.6898. Min Act: -0.1700
Data Index: 8187584 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0648. Min Range: -6.0648
Max Act: 5.6898. Min Act: -0.1700
Data Index: 6396186 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0648. Min Range: -6.0648
Max Act: 5.6898. Min Act: -0.1700
Data Index: 5737711 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0648. Min Range: -6.0648
Max Act: 5.6585. Min Act: -0.1700
Data Index: 324737 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0648. Min Range: -6.0648
Max Act: 5.6585. Min Act: -0.1700
Data Index: 1385131 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0648. Min Range: -6.0648
Max Act: 5.6273. Min Act: -0.1700
Data Index: 8708666 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0648. Min Range: -6.0648
Max Act: 5.6273. Min Act: -0.1700
Data Index: 4767488 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0648. Min Range: -6.0648
Max Act: 5.6273. Min Act: -0.1700
Data Index: 4061556 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0648. Min Range: -6.0648
Max Act: 5.6273. Min Act: -0.1700
Data Index: 3773644 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0648. Min Range: -6.0648
Max Act: 5.5960. Min Act: -0.1700
Data Index: 6075546 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19