Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.7288. Min Act: -0.1700
Data Index: 1152127 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.6975. Min Act: -0.1700
Data Index: 1619403 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.6663. Min Act: -0.1700
Data Index: 5029556 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.6663. Min Act: -0.1700
Data Index: 4517308 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.6038. Min Act: -0.1700
Data Index: 7866488 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.5725. Min Act: -0.1700
Data Index: 723187 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.5100. Min Act: -0.1700
Data Index: 567762 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.5100. Min Act: -0.1700
Data Index: 6610148 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.4475. Min Act: -0.1700
Data Index: 4434607 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.4788. Min Act: -0.1700
Data Index: 7474552 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.4475. Min Act: -0.1700
Data Index: 3007448 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.4475. Min Act: -0.1700
Data Index: 6276846 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.4163. Min Act: -0.1700
Data Index: 650286 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.3850. Min Act: -0.1700
Data Index: 2071020 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.4163. Min Act: -0.1700
Data Index: 4219285 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.4163. Min Act: -0.1700
Data Index: 3452877 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.4163. Min Act: -0.1700
Data Index: 4065137 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.4163. Min Act: -0.1700
Data Index: 3688812 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.4163. Min Act: -0.1700
Data Index: 1774106 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7288. Min Range: -5.7288
Max Act: 5.4163. Min Act: -0.1700
Data Index: 3706797 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19