Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2456 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2019. Min Range: -7.2019
Max Act: 7.2019. Min Act: -0.1700
Data Index: 5323849 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2019. Min Range: -7.2019
Max Act: 7.1394. Min Act: -0.1700
Data Index: 7146916 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2019. Min Range: -7.2019
Max Act: 7.0769. Min Act: -0.1700
Data Index: 3940864 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2019. Min Range: -7.2019
Max Act: 7.0769. Min Act: -0.1700
Data Index: 189312 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2019. Min Range: -7.2019
Max Act: 6.9206. Min Act: -0.1700
Data Index: 8026672 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2019. Min Range: -7.2019
Max Act: 6.8894. Min Act: -0.1700
Data Index: 2215507 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2019. Min Range: -7.2019
Max Act: 6.8894. Min Act: -0.1700
Data Index: 2215501 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2019. Min Range: -7.2019
Max Act: 6.8894. Min Act: -0.1700
Data Index: 2720357 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2019. Min Range: -7.2019
Max Act: 6.8269. Min Act: -0.1700
Data Index: 7327772 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2019. Min Range: -7.2019
Max Act: 6.8894. Min Act: -0.1700
Data Index: 3612406 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2019. Min Range: -7.2019
Max Act: 6.8269. Min Act: -0.1700
Data Index: 125414 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2019. Min Range: -7.2019
Max Act: 6.8269. Min Act: -0.1700
Data Index: 1276364 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2019. Min Range: -7.2019
Max Act: 6.7644. Min Act: -0.1700
Data Index: 7327759 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2019. Min Range: -7.2019
Max Act: 6.7956. Min Act: -0.1700
Data Index: 1276356 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2019. Min Range: -7.2019
Max Act: 6.7956. Min Act: -0.1700
Data Index: 6684935 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2019. Min Range: -7.2019
Max Act: 6.7644. Min Act: -0.1700
Data Index: 1694835 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2019. Min Range: -7.2019
Max Act: 6.7331. Min Act: -0.1700
Data Index: 3480451 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2019. Min Range: -7.2019
Max Act: 6.7644. Min Act: -0.1700
Data Index: 125406 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2019. Min Range: -7.2019
Max Act: 6.6706. Min Act: -0.1700
Data Index: 3410118 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2019. Min Range: -7.2019
Max Act: 6.6394. Min Act: -0.1700
Data Index: 2629227 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19