Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3465 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3646. Min Range: -5.3646
Max Act: 5.3646. Min Act: -0.1700
Data Index: 5211470 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3646. Min Range: -5.3646
Max Act: 5.2396. Min Act: -0.1700
Data Index: 5840724 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3646. Min Range: -5.3646
Max Act: 5.1459. Min Act: -0.1700
Data Index: 7189444 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3646. Min Range: -5.3646
Max Act: 5.1771. Min Act: -0.1700
Data Index: 797984 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3646. Min Range: -5.3646
Max Act: 5.1459. Min Act: -0.1700
Data Index: 5493162 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3646. Min Range: -5.3646
Max Act: 5.1146. Min Act: -0.1700
Data Index: 930214 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3646. Min Range: -5.3646
Max Act: 5.0834. Min Act: -0.1700
Data Index: 1794469 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3646. Min Range: -5.3646
Max Act: 5.1146. Min Act: -0.1700
Data Index: 6591477 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3646. Min Range: -5.3646
Max Act: 5.0521. Min Act: -0.1700
Data Index: 4001296 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3646. Min Range: -5.3646
Max Act: 5.0834. Min Act: -0.1700
Data Index: 6528524 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3646. Min Range: -5.3646
Max Act: 5.0521. Min Act: -0.1700
Data Index: 5386284 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3646. Min Range: -5.3646
Max Act: 4.9896. Min Act: -0.1700
Data Index: 3110559 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3646. Min Range: -5.3646
Max Act: 5.0209. Min Act: -0.1700
Data Index: 3061691 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3646. Min Range: -5.3646
Max Act: 4.9896. Min Act: -0.1700
Data Index: 4465289 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3646. Min Range: -5.3646
Max Act: 4.9584. Min Act: -0.1700
Data Index: 3424218 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3646. Min Range: -5.3646
Max Act: 4.9896. Min Act: -0.1700
Data Index: 2877568 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3646. Min Range: -5.3646
Max Act: 4.9896. Min Act: -0.1700
Data Index: 3003202 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3646. Min Range: -5.3646
Max Act: 4.9896. Min Act: -0.1700
Data Index: 1577288 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3646. Min Range: -5.3646
Max Act: 4.9896. Min Act: -0.1700
Data Index: 1576411 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3646. Min Range: -5.3646
Max Act: 4.9584. Min Act: -0.1700
Data Index: 2285465 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19