Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5059 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2720. Min Range: -6.2720
Max Act: 6.2720. Min Act: -0.1700
Data Index: 5967475 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2720. Min Range: -6.2720
Max Act: 6.1158. Min Act: -0.1700
Data Index: 612305 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2720. Min Range: -6.2720
Max Act: 6.1158. Min Act: -0.1700
Data Index: 3064257 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2720. Min Range: -6.2720
Max Act: 6.1158. Min Act: -0.1700
Data Index: 4181486 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2720. Min Range: -6.2720
Max Act: 6.0533. Min Act: -0.1700
Data Index: 4877474 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2720. Min Range: -6.2720
Max Act: 6.0533. Min Act: -0.1700
Data Index: 3688862 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2720. Min Range: -6.2720
Max Act: 6.0220. Min Act: -0.1700
Data Index: 7391227 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2720. Min Range: -6.2720
Max Act: 5.9908. Min Act: -0.1700
Data Index: 5606206 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2720. Min Range: -6.2720
Max Act: 5.9595. Min Act: -0.1700
Data Index: 5515801 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2720. Min Range: -6.2720
Max Act: 5.9283. Min Act: -0.1700
Data Index: 2912127 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2720. Min Range: -6.2720
Max Act: 5.8970. Min Act: -0.1700
Data Index: 3908474 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2720. Min Range: -6.2720
Max Act: 5.8345. Min Act: -0.1700
Data Index: 263641 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2720. Min Range: -6.2720
Max Act: 5.8658. Min Act: -0.1700
Data Index: 4197279 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2720. Min Range: -6.2720
Max Act: 5.8658. Min Act: -0.1700
Data Index: 7802654 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2720. Min Range: -6.2720
Max Act: 5.8345. Min Act: -0.1700
Data Index: 1968233 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2720. Min Range: -6.2720
Max Act: 5.8345. Min Act: -0.1700
Data Index: 2077331 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2720. Min Range: -6.2720
Max Act: 5.8345. Min Act: -0.1700
Data Index: 8744467 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2720. Min Range: -6.2720
Max Act: 5.8345. Min Act: -0.1700
Data Index: 7134361 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2720. Min Range: -6.2720
Max Act: 5.8033. Min Act: -0.1700
Data Index: 1422961 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2720. Min Range: -6.2720
Max Act: 5.8033. Min Act: -0.1700
Data Index: 6490766 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19