Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.3152. Min Act: -0.1700
Data Index: 8293832 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.2527. Min Act: -0.1700
Data Index: 4016297 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.2527. Min Act: -0.1700
Data Index: 6369961 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.1902. Min Act: -0.1700
Data Index: 3793823 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.1902. Min Act: -0.1700
Data Index: 5737130 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.1277. Min Act: -0.1700
Data Index: 4271241 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.1277. Min Act: -0.1700
Data Index: 660916 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.0965. Min Act: -0.1700
Data Index: 5121866 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.1902. Min Act: -0.1700
Data Index: 5233371 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.1902. Min Act: -0.1700
Data Index: 163299 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.0965. Min Act: -0.1700
Data Index: 1492698 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.0965. Min Act: -0.1700
Data Index: 6377459 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.0965. Min Act: -0.1700
Data Index: 54084 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.0965. Min Act: -0.1700
Data Index: 1647615 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.0652. Min Act: -0.1700
Data Index: 3170966 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.0965. Min Act: -0.1700
Data Index: 5963257 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.0340. Min Act: -0.1700
Data Index: 8656376 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.0652. Min Act: -0.1700
Data Index: 2940661 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.0027. Min Act: -0.1700
Data Index: 8255245 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3152. Min Range: -8.3152
Max Act: 8.0340. Min Act: -0.1700
Data Index: 1917704 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19