Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5650 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3466. Min Range: -8.3466
Max Act: 8.3466. Min Act: -0.1700
Data Index: 2426519 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3466. Min Range: -8.3466
Max Act: 8.2841. Min Act: -0.1700
Data Index: 7028996 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3466. Min Range: -8.3466
Max Act: 8.2529. Min Act: -0.1700
Data Index: 3969711 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3466. Min Range: -8.3466
Max Act: 8.2216. Min Act: -0.1700
Data Index: 1011441 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3466. Min Range: -8.3466
Max Act: 8.1904. Min Act: -0.1700
Data Index: 1650942 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3466. Min Range: -8.3466
Max Act: 8.1904. Min Act: -0.1700
Data Index: 2278810 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3466. Min Range: -8.3466
Max Act: 8.0341. Min Act: -0.1700
Data Index: 8227197 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3466. Min Range: -8.3466
Max Act: 8.0029. Min Act: -0.1700
Data Index: 7739852 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3466. Min Range: -8.3466
Max Act: 7.9404. Min Act: -0.1700
Data Index: 3037442 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3466. Min Range: -8.3466
Max Act: 7.8466. Min Act: -0.1700
Data Index: 2426518 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3466. Min Range: -8.3466
Max Act: 7.8154. Min Act: -0.1700
Data Index: 6792757 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3466. Min Range: -8.3466
Max Act: 7.7529. Min Act: -0.1700
Data Index: 4287724 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3466. Min Range: -8.3466
Max Act: 7.7841. Min Act: -0.1700
Data Index: 3780465 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3466. Min Range: -8.3466
Max Act: 7.7529. Min Act: -0.1700
Data Index: 5245705 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3466. Min Range: -8.3466
Max Act: 7.7216. Min Act: -0.1700
Data Index: 1650943 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3466. Min Range: -8.3466
Max Act: 7.6591. Min Act: -0.1700
Data Index: 6072611 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3466. Min Range: -8.3466
Max Act: 7.6591. Min Act: -0.1700
Data Index: 5652942 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3466. Min Range: -8.3466
Max Act: 7.5966. Min Act: -0.1700
Data Index: 1867723 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3466. Min Range: -8.3466
Max Act: 7.5966. Min Act: -0.1700
Data Index: 7660651 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3466. Min Range: -8.3466
Max Act: 7.5654. Min Act: -0.1700
Data Index: 7133815 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19