Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2025 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5134. Min Range: -7.5134
Max Act: 7.5134. Min Act: -0.1700
Data Index: 809697 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5134. Min Range: -7.5134
Max Act: 7.2947. Min Act: -0.1700
Data Index: 7045243 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5134. Min Range: -7.5134
Max Act: 7.1384. Min Act: -0.1700
Data Index: 4453244 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5134. Min Range: -7.5134
Max Act: 7.0759. Min Act: -0.1700
Data Index: 8785889 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5134. Min Range: -7.5134
Max Act: 7.0134. Min Act: -0.1700
Data Index: 8431865 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5134. Min Range: -7.5134
Max Act: 6.9509. Min Act: -0.1700
Data Index: 4164714 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5134. Min Range: -7.5134
Max Act: 6.9509. Min Act: -0.1700
Data Index: 5979746 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5134. Min Range: -7.5134
Max Act: 6.9197. Min Act: -0.1700
Data Index: 8084888 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5134. Min Range: -7.5134
Max Act: 6.8259. Min Act: -0.1700
Data Index: 138689 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5134. Min Range: -7.5134
Max Act: 6.7634. Min Act: -0.1700
Data Index: 3849534 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5134. Min Range: -7.5134
Max Act: 6.7634. Min Act: -0.1700
Data Index: 6595842 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5134. Min Range: -7.5134
Max Act: 6.7322. Min Act: -0.1700
Data Index: 3458931 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5134. Min Range: -7.5134
Max Act: 6.7322. Min Act: -0.1700
Data Index: 3007827 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5134. Min Range: -7.5134
Max Act: 6.7322. Min Act: -0.1700
Data Index: 6612911 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5134. Min Range: -7.5134
Max Act: 6.7634. Min Act: -0.1700
Data Index: 3223510 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5134. Min Range: -7.5134
Max Act: 6.7322. Min Act: -0.1700
Data Index: 6704912 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5134. Min Range: -7.5134
Max Act: 6.7322. Min Act: -0.1700
Data Index: 6029283 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5134. Min Range: -7.5134
Max Act: 6.6697. Min Act: -0.1700
Data Index: 3471423 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5134. Min Range: -7.5134
Max Act: 6.6697. Min Act: -0.1700
Data Index: 1257088 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5134. Min Range: -7.5134
Max Act: 6.6384. Min Act: -0.1700
Data Index: 6474393 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19