Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4535 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3626. Min Range: -7.3626
Max Act: 7.3626. Min Act: -0.1700
Data Index: 7288665 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3626. Min Range: -7.3626
Max Act: 7.2688. Min Act: -0.1700
Data Index: 2258842 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3626. Min Range: -7.3626
Max Act: 7.2376. Min Act: -0.1700
Data Index: 6123688 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3626. Min Range: -7.3626
Max Act: 7.0501. Min Act: -0.1700
Data Index: 3474110 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3626. Min Range: -7.3626
Max Act: 7.0501. Min Act: -0.1700
Data Index: 8440901 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3626. Min Range: -7.3626
Max Act: 7.0188. Min Act: -0.1700
Data Index: 1845583 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3626. Min Range: -7.3626
Max Act: 7.0188. Min Act: -0.1700
Data Index: 5449576 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3626. Min Range: -7.3626
Max Act: 6.9876. Min Act: -0.1700
Data Index: 8742434 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3626. Min Range: -7.3626
Max Act: 6.9563. Min Act: -0.1700
Data Index: 1318657 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3626. Min Range: -7.3626
Max Act: 6.9251. Min Act: -0.1700
Data Index: 2629996 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3626. Min Range: -7.3626
Max Act: 6.9251. Min Act: -0.1700
Data Index: 8194849 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3626. Min Range: -7.3626
Max Act: 6.8938. Min Act: -0.1700
Data Index: 7674101 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3626. Min Range: -7.3626
Max Act: 6.8938. Min Act: -0.1700
Data Index: 6635464 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3626. Min Range: -7.3626
Max Act: 6.8938. Min Act: -0.1700
Data Index: 3674405 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3626. Min Range: -7.3626
Max Act: 6.8938. Min Act: -0.1700
Data Index: 2141313 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3626. Min Range: -7.3626
Max Act: 6.8001. Min Act: -0.1700
Data Index: 4776439 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3626. Min Range: -7.3626
Max Act: 6.8001. Min Act: -0.1700
Data Index: 3466540 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3626. Min Range: -7.3626
Max Act: 6.8001. Min Act: -0.1700
Data Index: 3146370 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3626. Min Range: -7.3626
Max Act: 6.8001. Min Act: -0.1700
Data Index: 7855065 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3626. Min Range: -7.3626
Max Act: 6.7688. Min Act: -0.1700
Data Index: 4920150 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19