Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4818 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0838. Min Range: -5.0838
Max Act: 5.0838. Min Act: -0.1700
Data Index: 4668106 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0838. Min Range: -5.0838
Max Act: 5.0213. Min Act: -0.1700
Data Index: 407862 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0838. Min Range: -5.0838
Max Act: 4.9901. Min Act: -0.1700
Data Index: 7399614 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0838. Min Range: -5.0838
Max Act: 4.9588. Min Act: -0.1700
Data Index: 1456407 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0838. Min Range: -5.0838
Max Act: 4.9588. Min Act: -0.1700
Data Index: 4982367 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0838. Min Range: -5.0838
Max Act: 4.9276. Min Act: -0.1700
Data Index: 1173379 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0838. Min Range: -5.0838
Max Act: 4.8651. Min Act: -0.1700
Data Index: 3097540 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0838. Min Range: -5.0838
Max Act: 4.8651. Min Act: -0.1700
Data Index: 6579427 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0838. Min Range: -5.0838
Max Act: 4.8963. Min Act: -0.1700
Data Index: 421230 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0838. Min Range: -5.0838
Max Act: 4.8338. Min Act: -0.1700
Data Index: 2535886 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0838. Min Range: -5.0838
Max Act: 4.8338. Min Act: -0.1700
Data Index: 4578752 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0838. Min Range: -5.0838
Max Act: 4.8338. Min Act: -0.1700
Data Index: 3117160 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0838. Min Range: -5.0838
Max Act: 4.8026. Min Act: -0.1700
Data Index: 8214 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0838. Min Range: -5.0838
Max Act: 4.8651. Min Act: -0.1700
Data Index: 1683834 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0838. Min Range: -5.0838
Max Act: 4.8026. Min Act: -0.1700
Data Index: 5226234 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0838. Min Range: -5.0838
Max Act: 4.7713. Min Act: -0.1700
Data Index: 4499522 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0838. Min Range: -5.0838
Max Act: 4.8026. Min Act: -0.1700
Data Index: 2624631 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0838. Min Range: -5.0838
Max Act: 4.7713. Min Act: -0.1700
Data Index: 5036953 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0838. Min Range: -5.0838
Max Act: 4.8026. Min Act: -0.1700
Data Index: 7036107 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0838. Min Range: -5.0838
Max Act: 4.8026. Min Act: -0.1700
Data Index: 3676229 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19