Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2214 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.3417. Min Act: -0.1700
Data Index: 5328525 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.2759. Min Act: -0.1700
Data Index: 4047907 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.2759. Min Act: -0.1700
Data Index: 7151623 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.2429. Min Act: -0.1700
Data Index: 4121454 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.2429. Min Act: -0.1700
Data Index: 5857878 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.2264. Min Act: -0.1700
Data Index: 685211 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.2264. Min Act: -0.1700
Data Index: 1903774 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.2264. Min Act: -0.1700
Data Index: 5817664 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.1932. Min Act: -0.1700
Data Index: 1025779 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.2098. Min Act: -0.1700
Data Index: 4288284 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.1766. Min Act: -0.1700
Data Index: 4407575 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.1932. Min Act: -0.1700
Data Index: 4355811 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.1932. Min Act: -0.1700
Data Index: 4026623 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.1766. Min Act: -0.1700
Data Index: 1667741 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.1766. Min Act: -0.1700
Data Index: 4288283 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.1766. Min Act: -0.1700
Data Index: 4380045 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.1766. Min Act: -0.1700
Data Index: 7762678 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.1600. Min Act: -0.1700
Data Index: 3532556 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.1600. Min Act: -0.1700
Data Index: 3099666 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.1600. Min Act: -0.1700
Data Index: 7008894 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19