Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4931 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.9570. Min Act: -0.1700
Data Index: 476255 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.8788. Min Act: -0.1700
Data Index: 7026378 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.8163. Min Act: -0.1700
Data Index: 6541656 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.8007. Min Act: -0.1700
Data Index: 3835383 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.7538. Min Act: -0.1700
Data Index: 5953121 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.7381. Min Act: -0.1700
Data Index: 1344933 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.6755. Min Act: -0.1700
Data Index: 1348554 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.6755. Min Act: -0.1700
Data Index: 266354 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.6599. Min Act: -0.1700
Data Index: 912908 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.6443. Min Act: -0.1700
Data Index: 2072094 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.6286. Min Act: -0.1700
Data Index: 3570345 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.6286. Min Act: -0.1700
Data Index: 1180966 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.6130. Min Act: -0.1700
Data Index: 1245030 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.6130. Min Act: -0.1700
Data Index: 7487107 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.5817. Min Act: -0.1700
Data Index: 8759362 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.5817. Min Act: -0.1700
Data Index: 8684382 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.5660. Min Act: -0.1700
Data Index: 4075590 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.5817. Min Act: -0.1700
Data Index: 7860424 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.5817. Min Act: -0.1700
Data Index: 1011598 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9570. Min Range: -3.9570
Max Act: 3.5660. Min Act: -0.1700
Data Index: 8302098 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19