Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3698 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3617. Min Range: -6.3617
Max Act: 6.3617. Min Act: -0.1700
Data Index: 3278409 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3617. Min Range: -6.3617
Max Act: 6.2992. Min Act: -0.1700
Data Index: 6790378 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3617. Min Range: -6.3617
Max Act: 6.0180. Min Act: -0.1700
Data Index: 8822463 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3617. Min Range: -6.3617
Max Act: 5.9555. Min Act: -0.1700
Data Index: 2481016 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3617. Min Range: -6.3617
Max Act: 5.9555. Min Act: -0.1700
Data Index: 8822464 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3617. Min Range: -6.3617
Max Act: 5.9555. Min Act: -0.1700
Data Index: 1824517 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3617. Min Range: -6.3617
Max Act: 5.9242. Min Act: -0.1700
Data Index: 6377982 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3617. Min Range: -6.3617
Max Act: 5.9242. Min Act: -0.1700
Data Index: 657912 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3617. Min Range: -6.3617
Max Act: 5.9242. Min Act: -0.1700
Data Index: 7695415 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3617. Min Range: -6.3617
Max Act: 5.8617. Min Act: -0.1700
Data Index: 1995367 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3617. Min Range: -6.3617
Max Act: 5.8305. Min Act: -0.1700
Data Index: 5840421 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3617. Min Range: -6.3617
Max Act: 5.8305. Min Act: -0.1700
Data Index: 783487 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3617. Min Range: -6.3617
Max Act: 5.8305. Min Act: -0.1700
Data Index: 6844428 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3617. Min Range: -6.3617
Max Act: 5.8305. Min Act: -0.1700
Data Index: 2046500 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3617. Min Range: -6.3617
Max Act: 5.7367. Min Act: -0.1700
Data Index: 2330098 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3617. Min Range: -6.3617
Max Act: 5.7367. Min Act: -0.1700
Data Index: 5883010 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3617. Min Range: -6.3617
Max Act: 5.7055. Min Act: -0.1700
Data Index: 5548260 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3617. Min Range: -6.3617
Max Act: 5.6742. Min Act: -0.1700
Data Index: 5680022 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3617. Min Range: -6.3617
Max Act: 5.7367. Min Act: -0.1700
Data Index: 2972694 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3617. Min Range: -6.3617
Max Act: 5.7367. Min Act: -0.1700
Data Index: 5438182 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19