Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3039 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1481. Min Range: -6.1481
Max Act: 6.1481. Min Act: -0.1700
Data Index: 4808905 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.9919. Min Act: -0.1700
Data Index: 4211171 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.9606. Min Act: -0.1700
Data Index: 5296046 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.9294. Min Act: -0.1700
Data Index: 4091081 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.9606. Min Act: -0.1700
Data Index: 2603555 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.8981. Min Act: -0.1700
Data Index: 1649177 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.8981. Min Act: -0.1700
Data Index: 8030280 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.8981. Min Act: -0.1700
Data Index: 6386979 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.8669. Min Act: -0.1700
Data Index: 4049498 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.8669. Min Act: -0.1700
Data Index: 6919378 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.8669. Min Act: -0.1700
Data Index: 361891 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.8669. Min Act: -0.1700
Data Index: 415553 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.8669. Min Act: -0.1700
Data Index: 7292438 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.8044. Min Act: -0.1700
Data Index: 1861683 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.8044. Min Act: -0.1700
Data Index: 8515519 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.8044. Min Act: -0.1700
Data Index: 7958661 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.7731. Min Act: -0.1700
Data Index: 6260376 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.7731. Min Act: -0.1700
Data Index: 4697071 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.7731. Min Act: -0.1700
Data Index: 313825 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1481. Min Range: -6.1481
Max Act: 5.7731. Min Act: -0.1700
Data Index: 4646020 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19