Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3058 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.7977. Min Act: -0.1700
Data Index: 1510012 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.5790. Min Act: -0.1700
Data Index: 6591238 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.2977. Min Act: -0.1700
Data Index: 5980837 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.2665. Min Act: -0.1700
Data Index: 4721085 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.2665. Min Act: -0.1700
Data Index: 8285551 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.1727. Min Act: -0.1700
Data Index: 6877556 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.1727. Min Act: -0.1700
Data Index: 6218395 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.1102. Min Act: -0.1700
Data Index: 8493706 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.1102. Min Act: -0.1700
Data Index: 2995623 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.1102. Min Act: -0.1700
Data Index: 6680582 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.1102. Min Act: -0.1700
Data Index: 7718809 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.0477. Min Act: -0.1700
Data Index: 645946 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.0165. Min Act: -0.1700
Data Index: 2754104 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.0477. Min Act: -0.1700
Data Index: 5208491 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.0165. Min Act: -0.1700
Data Index: 228960 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.0165. Min Act: -0.1700
Data Index: 5458649 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.0165. Min Act: -0.1700
Data Index: 668904 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7977. Min Range: -7.7977
Max Act: 6.9540. Min Act: -0.1700
Data Index: 6204166 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7977. Min Range: -7.7977
Max Act: 6.9540. Min Act: -0.1700
Data Index: 88633 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7977. Min Range: -7.7977
Max Act: 6.9227. Min Act: -0.1700
Data Index: 349054 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19