Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1713 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0364. Min Range: -3.0364
Max Act: 3.0364. Min Act: -0.1700
Data Index: 1829751 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0364. Min Range: -3.0364
Max Act: 3.0364. Min Act: -0.1700
Data Index: 664352 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0364. Min Range: -3.0364
Max Act: 3.0364. Min Act: -0.1700
Data Index: 4412765 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0364. Min Range: -3.0364
Max Act: 3.0364. Min Act: -0.1700
Data Index: 599012 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0364. Min Range: -3.0364
Max Act: 3.0206. Min Act: -0.1700
Data Index: 1276038 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0364. Min Range: -3.0364
Max Act: 3.0048. Min Act: -0.1700
Data Index: 3693489 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0364. Min Range: -3.0364
Max Act: 2.9890. Min Act: -0.1700
Data Index: 8055199 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0364. Min Range: -3.0364
Max Act: 2.9732. Min Act: -0.1700
Data Index: 8427335 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0364. Min Range: -3.0364
Max Act: 2.9732. Min Act: -0.1700
Data Index: 2319746 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0364. Min Range: -3.0364
Max Act: 2.9574. Min Act: -0.1700
Data Index: 3379380 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0364. Min Range: -3.0364
Max Act: 2.9574. Min Act: -0.1700
Data Index: 5867854 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0364. Min Range: -3.0364
Max Act: 2.9574. Min Act: -0.1700
Data Index: 7135623 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0364. Min Range: -3.0364
Max Act: 2.9574. Min Act: -0.1700
Data Index: 4294347 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0364. Min Range: -3.0364
Max Act: 2.9574. Min Act: -0.1700
Data Index: 4495624 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0364. Min Range: -3.0364
Max Act: 2.9415. Min Act: -0.1700
Data Index: 1117700 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0364. Min Range: -3.0364
Max Act: 2.9574. Min Act: -0.1700
Data Index: 8671430 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0364. Min Range: -3.0364
Max Act: 2.9415. Min Act: -0.1700
Data Index: 5526552 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0364. Min Range: -3.0364
Max Act: 2.9415. Min Act: -0.1700
Data Index: 2503954 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0364. Min Range: -3.0364
Max Act: 2.9415. Min Act: -0.1700
Data Index: 4019233 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0364. Min Range: -3.0364
Max Act: 2.9415. Min Act: -0.1700
Data Index: 1293575 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19