Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3705 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5508. Min Range: -8.5508
Max Act: 8.5508. Min Act: -0.1700
Data Index: 6957871 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5508. Min Range: -8.5508
Max Act: 8.4258. Min Act: -0.1700
Data Index: 3014159 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5508. Min Range: -8.5508
Max Act: 8.3633. Min Act: -0.1700
Data Index: 2752644 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5508. Min Range: -8.5508
Max Act: 8.3008. Min Act: -0.1700
Data Index: 5476024 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5508. Min Range: -8.5508
Max Act: 8.0195. Min Act: -0.1700
Data Index: 5882074 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5508. Min Range: -8.5508
Max Act: 7.8945. Min Act: -0.1700
Data Index: 2135743 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5508. Min Range: -8.5508
Max Act: 7.8633. Min Act: -0.1700
Data Index: 2965412 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5508. Min Range: -8.5508
Max Act: 7.7383. Min Act: -0.1700
Data Index: 2504615 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5508. Min Range: -8.5508
Max Act: 7.6758. Min Act: -0.1700
Data Index: 1108229 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5508. Min Range: -8.5508
Max Act: 7.6758. Min Act: -0.1700
Data Index: 4421331 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5508. Min Range: -8.5508
Max Act: 7.6133. Min Act: -0.1700
Data Index: 1188045 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5508. Min Range: -8.5508
Max Act: 7.6133. Min Act: -0.1700
Data Index: 7526057 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5508. Min Range: -8.5508
Max Act: 7.6133. Min Act: -0.1700
Data Index: 5636816 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5508. Min Range: -8.5508
Max Act: 7.6133. Min Act: -0.1700
Data Index: 8356677 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5508. Min Range: -8.5508
Max Act: 7.5508. Min Act: -0.1700
Data Index: 7696129 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5508. Min Range: -8.5508
Max Act: 7.5508. Min Act: -0.1700
Data Index: 7377395 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5508. Min Range: -8.5508
Max Act: 7.5195. Min Act: -0.1700
Data Index: 4471327 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5508. Min Range: -8.5508
Max Act: 7.5195. Min Act: -0.1700
Data Index: 2425761 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5508. Min Range: -8.5508
Max Act: 7.5195. Min Act: -0.1700
Data Index: 1536731 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5508. Min Range: -8.5508
Max Act: 7.4883. Min Act: -0.1700
Data Index: 5099676 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19