Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5734 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5497. Min Range: -6.5497
Max Act: 6.5497. Min Act: -0.1700
Data Index: 251640 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5497. Min Range: -6.5497
Max Act: 6.4559. Min Act: -0.1700
Data Index: 240369 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5497. Min Range: -6.5497
Max Act: 6.0497. Min Act: -0.1700
Data Index: 4668647 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5497. Min Range: -6.5497
Max Act: 6.0184. Min Act: -0.1700
Data Index: 5885530 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5497. Min Range: -6.5497
Max Act: 6.0184. Min Act: -0.1700
Data Index: 2245371 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5497. Min Range: -6.5497
Max Act: 6.0184. Min Act: -0.1700
Data Index: 912910 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5497. Min Range: -6.5497
Max Act: 5.9872. Min Act: -0.1700
Data Index: 5400412 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5497. Min Range: -6.5497
Max Act: 5.9872. Min Act: -0.1700
Data Index: 4693384 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5497. Min Range: -6.5497
Max Act: 5.9559. Min Act: -0.1700
Data Index: 8657077 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5497. Min Range: -6.5497
Max Act: 5.9247. Min Act: -0.1700
Data Index: 1690115 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5497. Min Range: -6.5497
Max Act: 5.8934. Min Act: -0.1700
Data Index: 5738281 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5497. Min Range: -6.5497
Max Act: 5.9247. Min Act: -0.1700
Data Index: 1181385 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5497. Min Range: -6.5497
Max Act: 5.8622. Min Act: -0.1700
Data Index: 5520826 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5497. Min Range: -6.5497
Max Act: 5.8622. Min Act: -0.1700
Data Index: 1761925 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5497. Min Range: -6.5497
Max Act: 5.8622. Min Act: -0.1700
Data Index: 4467387 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5497. Min Range: -6.5497
Max Act: 5.8622. Min Act: -0.1700
Data Index: 6361079 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5497. Min Range: -6.5497
Max Act: 5.8622. Min Act: -0.1700
Data Index: 1116629 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5497. Min Range: -6.5497
Max Act: 5.7997. Min Act: -0.1700
Data Index: 3384644 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5497. Min Range: -6.5497
Max Act: 5.8309. Min Act: -0.1700
Data Index: 1342236 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5497. Min Range: -6.5497
Max Act: 5.7997. Min Act: -0.1700
Data Index: 1748512 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19