Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 407 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.7888. Min Act: -0.1700
Data Index: 3795267 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.7263. Min Act: -0.1700
Data Index: 252540 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.6013. Min Act: -0.1700
Data Index: 3778309 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.6013. Min Act: -0.1700
Data Index: 5442689 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.6013. Min Act: -0.1700
Data Index: 7218318 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.5700. Min Act: -0.1700
Data Index: 2896519 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.4450. Min Act: -0.1700
Data Index: 601057 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.3825. Min Act: -0.1700
Data Index: 2982182 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.3513. Min Act: -0.1700
Data Index: 6939920 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.3513. Min Act: -0.1700
Data Index: 864896 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.3200. Min Act: -0.1700
Data Index: 3932465 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.2888. Min Act: -0.1700
Data Index: 5682919 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.2575. Min Act: -0.1700
Data Index: 3477487 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.2888. Min Act: -0.1700
Data Index: 971070 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.2575. Min Act: -0.1700
Data Index: 5847027 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.1950. Min Act: -0.1700
Data Index: 3885984 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.1950. Min Act: -0.1700
Data Index: 5847023 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.2263. Min Act: -0.1700
Data Index: 5440754 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.2263. Min Act: -0.1700
Data Index: 437608 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7888. Min Range: -5.7888
Max Act: 5.1950. Min Act: -0.1700
Data Index: 4287164 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19