Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5431 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.5393. Min Act: -0.1700
Data Index: 5547945 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.4143. Min Act: -0.1700
Data Index: 8133693 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.3518. Min Act: -0.1700
Data Index: 4821434 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.2893. Min Act: -0.1700
Data Index: 7501201 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.2893. Min Act: -0.1700
Data Index: 6168266 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.2893. Min Act: -0.1700
Data Index: 3544476 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.1643. Min Act: -0.1700
Data Index: 4660851 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.1643. Min Act: -0.1700
Data Index: 1943834 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.1018. Min Act: -0.1700
Data Index: 5624093 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.1018. Min Act: -0.1700
Data Index: 289485 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.0705. Min Act: -0.1700
Data Index: 3315065 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.0393. Min Act: -0.1700
Data Index: 5376620 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.0393. Min Act: -0.1700
Data Index: 1566000 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.0393. Min Act: -0.1700
Data Index: 4854622 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.0080. Min Act: -0.1700
Data Index: 6482275 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.0393. Min Act: -0.1700
Data Index: 3970200 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.0080. Min Act: -0.1700
Data Index: 8713556 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5393. Min Range: -6.5393
Max Act: 5.9768. Min Act: -0.1700
Data Index: 5516016 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5393. Min Range: -6.5393
Max Act: 5.9455. Min Act: -0.1700
Data Index: 5318565 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5393. Min Range: -6.5393
Max Act: 5.9455. Min Act: -0.1700
Data Index: 2767952 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19