Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1247 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.7200. Min Act: -0.1700
Data Index: 6553046 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.4700. Min Act: -0.1700
Data Index: 1490944 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.4700. Min Act: -0.1700
Data Index: 855615 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.4075. Min Act: -0.1700
Data Index: 1340785 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.3763. Min Act: -0.1700
Data Index: 7396212 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.4075. Min Act: -0.1700
Data Index: 4274154 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.4388. Min Act: -0.1700
Data Index: 5410663 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.3763. Min Act: -0.1700
Data Index: 4371816 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.3450. Min Act: -0.1700
Data Index: 3831938 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.3763. Min Act: -0.1700
Data Index: 7337750 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.3450. Min Act: -0.1700
Data Index: 7570960 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.3450. Min Act: -0.1700
Data Index: 4437350 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.3450. Min Act: -0.1700
Data Index: 7603373 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.3138. Min Act: -0.1700
Data Index: 1100171 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.3138. Min Act: -0.1700
Data Index: 737957 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.2825. Min Act: -0.1700
Data Index: 2355130 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.2825. Min Act: -0.1700
Data Index: 1015041 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.2825. Min Act: -0.1700
Data Index: 186876 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.2513. Min Act: -0.1700
Data Index: 5859271 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7200. Min Range: -6.7200
Max Act: 6.2825. Min Act: -0.1700
Data Index: 595287 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19