Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4858. Min Range: -6.4858
Max Act: 6.4858. Min Act: -0.1700
Data Index: 8134355 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4858. Min Range: -6.4858
Max Act: 6.4233. Min Act: -0.1700
Data Index: 4211954 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4858. Min Range: -6.4858
Max Act: 6.3608. Min Act: -0.1700
Data Index: 7610140 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4858. Min Range: -6.4858
Max Act: 6.2983. Min Act: -0.1700
Data Index: 7081485 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4858. Min Range: -6.4858
Max Act: 6.2358. Min Act: -0.1700
Data Index: 2102100 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4858. Min Range: -6.4858
Max Act: 6.2045. Min Act: -0.1700
Data Index: 6224991 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4858. Min Range: -6.4858
Max Act: 6.1420. Min Act: -0.1700
Data Index: 166902 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4858. Min Range: -6.4858
Max Act: 6.0795. Min Act: -0.1700
Data Index: 7010276 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4858. Min Range: -6.4858
Max Act: 6.0483. Min Act: -0.1700
Data Index: 7376783 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4858. Min Range: -6.4858
Max Act: 6.0483. Min Act: -0.1700
Data Index: 5561864 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4858. Min Range: -6.4858
Max Act: 6.0795. Min Act: -0.1700
Data Index: 6625551 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4858. Min Range: -6.4858
Max Act: 6.0170. Min Act: -0.1700
Data Index: 1971798 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4858. Min Range: -6.4858
Max Act: 6.0170. Min Act: -0.1700
Data Index: 2753677 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4858. Min Range: -6.4858
Max Act: 5.9858. Min Act: -0.1700
Data Index: 2530218 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4858. Min Range: -6.4858
Max Act: 5.9858. Min Act: -0.1700
Data Index: 1581454 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4858. Min Range: -6.4858
Max Act: 5.9545. Min Act: -0.1700
Data Index: 117373 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4858. Min Range: -6.4858
Max Act: 5.9233. Min Act: -0.1700
Data Index: 4450788 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4858. Min Range: -6.4858
Max Act: 5.9545. Min Act: -0.1700
Data Index: 1432012 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4858. Min Range: -6.4858
Max Act: 5.9545. Min Act: -0.1700
Data Index: 4734696 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4858. Min Range: -6.4858
Max Act: 5.9233. Min Act: -0.1700
Data Index: 6379400 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19