Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5956 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5617. Min Range: -7.5617
Max Act: 7.5617. Min Act: -0.1700
Data Index: 4043262 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5617. Min Range: -7.5617
Max Act: 7.4055. Min Act: -0.1700
Data Index: 6146065 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5617. Min Range: -7.5617
Max Act: 7.2805. Min Act: -0.1700
Data Index: 576666 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5617. Min Range: -7.5617
Max Act: 7.2180. Min Act: -0.1700
Data Index: 138256 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5617. Min Range: -7.5617
Max Act: 7.1867. Min Act: -0.1700
Data Index: 8171423 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5617. Min Range: -7.5617
Max Act: 7.1555. Min Act: -0.1700
Data Index: 1301797 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5617. Min Range: -7.5617
Max Act: 7.1555. Min Act: -0.1700
Data Index: 2464393 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5617. Min Range: -7.5617
Max Act: 7.0930. Min Act: -0.1700
Data Index: 4072725 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5617. Min Range: -7.5617
Max Act: 7.0617. Min Act: -0.1700
Data Index: 3395678 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5617. Min Range: -7.5617
Max Act: 7.0617. Min Act: -0.1700
Data Index: 5497137 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5617. Min Range: -7.5617
Max Act: 7.0617. Min Act: -0.1700
Data Index: 1120704 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5617. Min Range: -7.5617
Max Act: 7.0305. Min Act: -0.1700
Data Index: 3000080 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5617. Min Range: -7.5617
Max Act: 7.0305. Min Act: -0.1700
Data Index: 7535221 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5617. Min Range: -7.5617
Max Act: 6.9680. Min Act: -0.1700
Data Index: 8043312 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5617. Min Range: -7.5617
Max Act: 6.9992. Min Act: -0.1700
Data Index: 5561077 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5617. Min Range: -7.5617
Max Act: 6.9992. Min Act: -0.1700
Data Index: 8499159 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5617. Min Range: -7.5617
Max Act: 6.9680. Min Act: -0.1700
Data Index: 6427663 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5617. Min Range: -7.5617
Max Act: 6.9680. Min Act: -0.1700
Data Index: 1835549 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5617. Min Range: -7.5617
Max Act: 6.9992. Min Act: -0.1700
Data Index: 4267118 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5617. Min Range: -7.5617
Max Act: 6.9367. Min Act: -0.1700
Data Index: 8106497 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19