Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2538 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5336. Min Range: -4.5336
Max Act: 4.5336. Min Act: -0.1700
Data Index: 8001549 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5336. Min Range: -4.5336
Max Act: 4.3461. Min Act: -0.1700
Data Index: 559820 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5336. Min Range: -4.5336
Max Act: 4.2523. Min Act: -0.1700
Data Index: 8814706 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5336. Min Range: -4.5336
Max Act: 4.2211. Min Act: -0.1700
Data Index: 849837 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5336. Min Range: -4.5336
Max Act: 4.1586. Min Act: -0.1700
Data Index: 371662 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5336. Min Range: -4.5336
Max Act: 4.1586. Min Act: -0.1700
Data Index: 129672 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5336. Min Range: -4.5336
Max Act: 4.0961. Min Act: -0.1700
Data Index: 929430 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5336. Min Range: -4.5336
Max Act: 4.1273. Min Act: -0.1700
Data Index: 2343173 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5336. Min Range: -4.5336
Max Act: 4.0961. Min Act: -0.1700
Data Index: 4033441 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5336. Min Range: -4.5336
Max Act: 4.0648. Min Act: -0.1700
Data Index: 5023493 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5336. Min Range: -4.5336
Max Act: 4.0335. Min Act: -0.1700
Data Index: 8580914 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5336. Min Range: -4.5336
Max Act: 4.0335. Min Act: -0.1700
Data Index: 4229143 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5336. Min Range: -4.5336
Max Act: 4.0023. Min Act: -0.1700
Data Index: 6700949 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5336. Min Range: -4.5336
Max Act: 4.0648. Min Act: -0.1700
Data Index: 8499286 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5336. Min Range: -4.5336
Max Act: 4.0335. Min Act: -0.1700
Data Index: 371526 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5336. Min Range: -4.5336
Max Act: 3.9710. Min Act: -0.1700
Data Index: 7163885 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5336. Min Range: -4.5336
Max Act: 4.0023. Min Act: -0.1700
Data Index: 8318722 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5336. Min Range: -4.5336
Max Act: 3.9710. Min Act: -0.1700
Data Index: 5242159 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5336. Min Range: -4.5336
Max Act: 3.9710. Min Act: -0.1700
Data Index: 8800025 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5336. Min Range: -4.5336
Max Act: 3.9710. Min Act: -0.1700
Data Index: 4404459 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19