Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3055 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0758. Min Range: -8.0758
Max Act: 8.0758. Min Act: -0.1700
Data Index: 1359476 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.8571. Min Act: -0.1700
Data Index: 2585370 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.7946. Min Act: -0.1700
Data Index: 3847669 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.7946. Min Act: -0.1700
Data Index: 1271030 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.6071. Min Act: -0.1700
Data Index: 2798064 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.5758. Min Act: -0.1700
Data Index: 2494799 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.5446. Min Act: -0.1700
Data Index: 8827132 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.5133. Min Act: -0.1700
Data Index: 46678 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.4821. Min Act: -0.1700
Data Index: 608315 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.4821. Min Act: -0.1700
Data Index: 7976688 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.4196. Min Act: -0.1700
Data Index: 3350045 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.3571. Min Act: -0.1700
Data Index: 3864221 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.3258. Min Act: -0.1700
Data Index: 2354899 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.3258. Min Act: -0.1700
Data Index: 963651 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.3258. Min Act: -0.1700
Data Index: 5879350 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.2633. Min Act: -0.1700
Data Index: 256461 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.2008. Min Act: -0.1700
Data Index: 1654374 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.2321. Min Act: -0.1700
Data Index: 4568710 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.2008. Min Act: -0.1700
Data Index: 8770084 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0758. Min Range: -8.0758
Max Act: 7.1696. Min Act: -0.1700
Data Index: 7638087 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19