Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1559 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0657. Min Range: -8.0657
Max Act: 8.0657. Min Act: -0.1700
Data Index: 628848 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.7532. Min Act: -0.1700
Data Index: 2362136 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.6282. Min Act: -0.1700
Data Index: 5604670 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.5657. Min Act: -0.1700
Data Index: 4313393 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.5970. Min Act: -0.1700
Data Index: 2796986 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.5345. Min Act: -0.1700
Data Index: 746637 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.5970. Min Act: -0.1700
Data Index: 4750146 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.5032. Min Act: -0.1700
Data Index: 6455090 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.5032. Min Act: -0.1700
Data Index: 4080583 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.4720. Min Act: -0.1700
Data Index: 250740 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.4407. Min Act: -0.1700
Data Index: 3164910 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.4407. Min Act: -0.1700
Data Index: 3663763 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.4407. Min Act: -0.1700
Data Index: 2194196 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.4095. Min Act: -0.1700
Data Index: 963025 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.4095. Min Act: -0.1700
Data Index: 6139306 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.3782. Min Act: -0.1700
Data Index: 3934777 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.3782. Min Act: -0.1700
Data Index: 1046676 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.3782. Min Act: -0.1700
Data Index: 1015907 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.3782. Min Act: -0.1700
Data Index: 1969410 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0657. Min Range: -8.0657
Max Act: 7.3470. Min Act: -0.1700
Data Index: 707698 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19