Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4471 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.8244. Min Act: -0.1700
Data Index: 687610 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.8244. Min Act: -0.1700
Data Index: 729593 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.7931. Min Act: -0.1700
Data Index: 5414618 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.7931. Min Act: -0.1700
Data Index: 279872 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.7619. Min Act: -0.1700
Data Index: 947960 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.7619. Min Act: -0.1700
Data Index: 5893631 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.6994. Min Act: -0.1700
Data Index: 7300121 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.7306. Min Act: -0.1700
Data Index: 8487484 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.7306. Min Act: -0.1700
Data Index: 1829175 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.6994. Min Act: -0.1700
Data Index: 5711062 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.6994. Min Act: -0.1700
Data Index: 7767279 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.6994. Min Act: -0.1700
Data Index: 750098 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.6994. Min Act: -0.1700
Data Index: 1138207 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.6681. Min Act: -0.1700
Data Index: 1555399 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.6994. Min Act: -0.1700
Data Index: 780644 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.6681. Min Act: -0.1700
Data Index: 4954391 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.6681. Min Act: -0.1700
Data Index: 7199579 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.6681. Min Act: -0.1700
Data Index: 1908341 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.6369. Min Act: -0.1700
Data Index: 1295172 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8244. Min Range: -4.8244
Max Act: 4.6369. Min Act: -0.1700
Data Index: 5388906 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19