Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 961 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1674. Min Range: -6.1674
Max Act: 6.1674. Min Act: -0.1700
Data Index: 3059495 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1674. Min Range: -6.1674
Max Act: 6.1049. Min Act: -0.1700
Data Index: 5958427 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1674. Min Range: -6.1674
Max Act: 6.1362. Min Act: -0.1700
Data Index: 7645208 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1674. Min Range: -6.1674
Max Act: 6.0424. Min Act: -0.1700
Data Index: 6510344 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1674. Min Range: -6.1674
Max Act: 6.0737. Min Act: -0.1700
Data Index: 3402021 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1674. Min Range: -6.1674
Max Act: 6.0112. Min Act: -0.1700
Data Index: 2738665 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1674. Min Range: -6.1674
Max Act: 5.9174. Min Act: -0.1700
Data Index: 3511908 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1674. Min Range: -6.1674
Max Act: 5.9487. Min Act: -0.1700
Data Index: 5531699 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1674. Min Range: -6.1674
Max Act: 5.8862. Min Act: -0.1700
Data Index: 6253211 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1674. Min Range: -6.1674
Max Act: 5.8862. Min Act: -0.1700
Data Index: 4529163 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1674. Min Range: -6.1674
Max Act: 5.8549. Min Act: -0.1700
Data Index: 513593 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1674. Min Range: -6.1674
Max Act: 5.7612. Min Act: -0.1700
Data Index: 3816693 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1674. Min Range: -6.1674
Max Act: 5.7924. Min Act: -0.1700
Data Index: 7813802 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1674. Min Range: -6.1674
Max Act: 5.7612. Min Act: -0.1700
Data Index: 3434254 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1674. Min Range: -6.1674
Max Act: 5.7299. Min Act: -0.1700
Data Index: 2864823 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1674. Min Range: -6.1674
Max Act: 5.6987. Min Act: -0.1700
Data Index: 1764599 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1674. Min Range: -6.1674
Max Act: 5.6987. Min Act: -0.1700
Data Index: 7504967 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1674. Min Range: -6.1674
Max Act: 5.7299. Min Act: -0.1700
Data Index: 7811561 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1674. Min Range: -6.1674
Max Act: 5.7299. Min Act: -0.1700
Data Index: 3367221 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1674. Min Range: -6.1674
Max Act: 5.7299. Min Act: -0.1700
Data Index: 1700726 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19