Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2525 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.9487. Min Act: -0.1700
Data Index: 15406 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.8862. Min Act: -0.1700
Data Index: 8777216 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.7924. Min Act: -0.1700
Data Index: 2178848 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.6987. Min Act: -0.1700
Data Index: 1689514 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.6987. Min Act: -0.1700
Data Index: 4842436 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.6674. Min Act: -0.1700
Data Index: 5227373 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.6674. Min Act: -0.1700
Data Index: 818588 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.6674. Min Act: -0.1700
Data Index: 6792057 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.6674. Min Act: -0.1700
Data Index: 3313154 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.6362. Min Act: -0.1700
Data Index: 6430454 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.6362. Min Act: -0.1700
Data Index: 344531 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.6362. Min Act: -0.1700
Data Index: 3564093 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.6362. Min Act: -0.1700
Data Index: 2031998 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.6362. Min Act: -0.1700
Data Index: 5942228 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.6362. Min Act: -0.1700
Data Index: 2654427 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.6049. Min Act: -0.1700
Data Index: 4694522 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.6049. Min Act: -0.1700
Data Index: 7892558 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.6362. Min Act: -0.1700
Data Index: 6143862 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.6049. Min Act: -0.1700
Data Index: 1868391 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9487. Min Range: -4.9487
Max Act: 4.6049. Min Act: -0.1700
Data Index: 5614947 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19