Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3425 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3242. Min Range: -5.3242
Max Act: 5.3242. Min Act: -0.1700
Data Index: 5330440 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3242. Min Range: -5.3242
Max Act: 5.1054. Min Act: -0.1700
Data Index: 953037 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3242. Min Range: -5.3242
Max Act: 5.1054. Min Act: -0.1700
Data Index: 6184101 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3242. Min Range: -5.3242
Max Act: 5.0742. Min Act: -0.1700
Data Index: 5219155 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3242. Min Range: -5.3242
Max Act: 5.0429. Min Act: -0.1700
Data Index: 1109390 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3242. Min Range: -5.3242
Max Act: 4.9804. Min Act: -0.1700
Data Index: 5488889 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3242. Min Range: -5.3242
Max Act: 4.9492. Min Act: -0.1700
Data Index: 32764 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3242. Min Range: -5.3242
Max Act: 4.9179. Min Act: -0.1700
Data Index: 4642523 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3242. Min Range: -5.3242
Max Act: 4.9179. Min Act: -0.1700
Data Index: 3752695 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3242. Min Range: -5.3242
Max Act: 4.8867. Min Act: -0.1700
Data Index: 5745832 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3242. Min Range: -5.3242
Max Act: 4.8554. Min Act: -0.1700
Data Index: 6368299 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3242. Min Range: -5.3242
Max Act: 4.8554. Min Act: -0.1700
Data Index: 2735342 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3242. Min Range: -5.3242
Max Act: 4.7929. Min Act: -0.1700
Data Index: 867135 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3242. Min Range: -5.3242
Max Act: 4.7617. Min Act: -0.1700
Data Index: 6081342 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3242. Min Range: -5.3242
Max Act: 4.7929. Min Act: -0.1700
Data Index: 5949620 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3242. Min Range: -5.3242
Max Act: 4.7929. Min Act: -0.1700
Data Index: 3132758 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3242. Min Range: -5.3242
Max Act: 4.7929. Min Act: -0.1700
Data Index: 3981539 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3242. Min Range: -5.3242
Max Act: 4.7617. Min Act: -0.1700
Data Index: 1704363 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3242. Min Range: -5.3242
Max Act: 4.7617. Min Act: -0.1700
Data Index: 3708941 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3242. Min Range: -5.3242
Max Act: 4.7617. Min Act: -0.1700
Data Index: 3740521 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19