Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 484 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0449. Min Range: -7.0449
Max Act: 7.0449. Min Act: -0.1700
Data Index: 5338838 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.7949. Min Act: -0.1700
Data Index: 5338837 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.7011. Min Act: -0.1700
Data Index: 1448201 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.4199. Min Act: -0.1700
Data Index: 4753712 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.3574. Min Act: -0.1700
Data Index: 4063788 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.3574. Min Act: -0.1700
Data Index: 4432332 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.3574. Min Act: -0.1700
Data Index: 1050764 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.3261. Min Act: -0.1700
Data Index: 4519491 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.2949. Min Act: -0.1700
Data Index: 3561844 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.2949. Min Act: -0.1700
Data Index: 7750598 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.2636. Min Act: -0.1700
Data Index: 6335643 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.2636. Min Act: -0.1700
Data Index: 7998170 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.2324. Min Act: -0.1700
Data Index: 419199 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.2011. Min Act: -0.1700
Data Index: 2589634 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.2011. Min Act: -0.1700
Data Index: 7238841 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.1386. Min Act: -0.1700
Data Index: 3381928 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.0761. Min Act: -0.1700
Data Index: 1522995 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.0761. Min Act: -0.1700
Data Index: 8249759 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.0761. Min Act: -0.1700
Data Index: 2084242 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0449. Min Range: -7.0449
Max Act: 6.0449. Min Act: -0.1700
Data Index: 5811801 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19