Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3891 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.9470. Min Act: -0.1700
Data Index: 2178433 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.8220. Min Act: -0.1700
Data Index: 4013638 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.8220. Min Act: -0.1700
Data Index: 8777053 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.7595. Min Act: -0.1700
Data Index: 1014013 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.6970. Min Act: -0.1700
Data Index: 8777057 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.6970. Min Act: -0.1700
Data Index: 5553803 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.6657. Min Act: -0.1700
Data Index: 2415639 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.6657. Min Act: -0.1700
Data Index: 631199 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.6657. Min Act: -0.1700
Data Index: 5935365 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.6032. Min Act: -0.1700
Data Index: 7502814 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.5720. Min Act: -0.1700
Data Index: 5229308 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.5095. Min Act: -0.1700
Data Index: 1094482 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.5095. Min Act: -0.1700
Data Index: 4274025 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.5095. Min Act: -0.1700
Data Index: 8704003 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.4470. Min Act: -0.1700
Data Index: 5523765 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.4782. Min Act: -0.1700
Data Index: 5801152 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.4782. Min Act: -0.1700
Data Index: 764527 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.4782. Min Act: -0.1700
Data Index: 1453355 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.4782. Min Act: -0.1700
Data Index: 7687969 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9470. Min Range: -5.9470
Max Act: 5.4470. Min Act: -0.1700
Data Index: 6726776 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19