Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2326 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.3475. Min Act: -0.1700
Data Index: 6191770 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.2538. Min Act: -0.1700
Data Index: 8198262 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.1913. Min Act: -0.1700
Data Index: 2347797 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.1913. Min Act: -0.1700
Data Index: 3766679 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.1288. Min Act: -0.1700
Data Index: 1836050 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.1600. Min Act: -0.1700
Data Index: 4718290 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.1913. Min Act: -0.1700
Data Index: 2995236 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.1600. Min Act: -0.1700
Data Index: 1553484 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.1288. Min Act: -0.1700
Data Index: 3153790 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.1288. Min Act: -0.1700
Data Index: 3412689 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.1288. Min Act: -0.1700
Data Index: 3012721 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.1288. Min Act: -0.1700
Data Index: 6726526 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.0975. Min Act: -0.1700
Data Index: 3095219 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.0975. Min Act: -0.1700
Data Index: 5673564 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.0975. Min Act: -0.1700
Data Index: 1194758 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.0663. Min Act: -0.1700
Data Index: 688386 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.0975. Min Act: -0.1700
Data Index: 3306673 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.0975. Min Act: -0.1700
Data Index: 6350139 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.0663. Min Act: -0.1700
Data Index: 7839795 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3475. Min Range: -5.3475
Max Act: 5.0663. Min Act: -0.1700
Data Index: 1281150 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19