Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4737 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.9132. Min Act: -0.1700
Data Index: 5793667 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.8819. Min Act: -0.1700
Data Index: 4992019 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.8194. Min Act: -0.1700
Data Index: 4992018 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.8194. Min Act: -0.1700
Data Index: 3313510 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.7882. Min Act: -0.1700
Data Index: 6551619 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.7569. Min Act: -0.1700
Data Index: 5793672 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.7257. Min Act: -0.1700
Data Index: 5793678 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.7257. Min Act: -0.1700
Data Index: 8152594 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.7257. Min Act: -0.1700
Data Index: 5983251 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.6632. Min Act: -0.1700
Data Index: 6130087 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.6319. Min Act: -0.1700
Data Index: 5257989 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.6319. Min Act: -0.1700
Data Index: 3730368 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.6007. Min Act: -0.1700
Data Index: 7751182 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.6007. Min Act: -0.1700
Data Index: 8058690 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.5694. Min Act: -0.1700
Data Index: 5233959 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.5694. Min Act: -0.1700
Data Index: 6092651 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.5694. Min Act: -0.1700
Data Index: 2440293 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.5694. Min Act: -0.1700
Data Index: 1155282 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.5694. Min Act: -0.1700
Data Index: 4637071 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.5382. Min Act: -0.1700
Data Index: 439397 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19