Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4484 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0276. Min Range: -6.0276
Max Act: 6.0276. Min Act: -0.1700
Data Index: 3876928 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.9963. Min Act: -0.1700
Data Index: 413094 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.9338. Min Act: -0.1700
Data Index: 6779481 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.9338. Min Act: -0.1700
Data Index: 2890393 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.8713. Min Act: -0.1700
Data Index: 4727712 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.8713. Min Act: -0.1700
Data Index: 4070469 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.8401. Min Act: -0.1700
Data Index: 435901 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.8088. Min Act: -0.1700
Data Index: 926517 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.7463. Min Act: -0.1700
Data Index: 982616 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.7463. Min Act: -0.1700
Data Index: 970600 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.7151. Min Act: -0.1700
Data Index: 7320734 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.7151. Min Act: -0.1700
Data Index: 8156261 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.6838. Min Act: -0.1700
Data Index: 7799220 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.6838. Min Act: -0.1700
Data Index: 3282001 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.6838. Min Act: -0.1700
Data Index: 7887136 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.6838. Min Act: -0.1700
Data Index: 3577421 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.6526. Min Act: -0.1700
Data Index: 2446609 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.6526. Min Act: -0.1700
Data Index: 2758288 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.6213. Min Act: -0.1700
Data Index: 6067416 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0276. Min Range: -6.0276
Max Act: 5.5901. Min Act: -0.1700
Data Index: 2224159 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19