Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3429 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.2661. Min Act: -0.1700
Data Index: 878688 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.2496. Min Act: -0.1700
Data Index: 1480861 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.2496. Min Act: -0.1700
Data Index: 8316333 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.2496. Min Act: -0.1700
Data Index: 7832075 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.2331. Min Act: -0.1700
Data Index: 3863507 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.2165. Min Act: -0.1700
Data Index: 6073674 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.1999. Min Act: -0.1700
Data Index: 1195182 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.1833. Min Act: -0.1700
Data Index: 3588678 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.1667. Min Act: -0.1700
Data Index: 5024401 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.1500. Min Act: -0.1700
Data Index: 8722867 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.1667. Min Act: -0.1700
Data Index: 5871234 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.1500. Min Act: -0.1700
Data Index: 2932356 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.1667. Min Act: -0.1700
Data Index: 7623740 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.1667. Min Act: -0.1700
Data Index: 3199782 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.1500. Min Act: -0.1700
Data Index: 3810928 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.1667. Min Act: -0.1700
Data Index: 7401089 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.1500. Min Act: -0.1700
Data Index: 1488380 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.1667. Min Act: -0.1700
Data Index: 4916371 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.1500. Min Act: -0.1700
Data Index: 5552525 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2661. Min Range: -2.2661
Max Act: 2.1333. Min Act: -0.1700
Data Index: 4916362 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19