Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4783 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.5664. Min Act: -0.1700
Data Index: 4006679 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.5352. Min Act: -0.1700
Data Index: 4006680 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.4414. Min Act: -0.1700
Data Index: 1097681 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.4102. Min Act: -0.1700
Data Index: 2077451 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.4102. Min Act: -0.1700
Data Index: 1097680 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.2852. Min Act: -0.1700
Data Index: 4810503 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.2539. Min Act: -0.1700
Data Index: 7709491 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.2227. Min Act: -0.1700
Data Index: 5427537 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.1914. Min Act: -0.1700
Data Index: 1518827 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.1289. Min Act: -0.1700
Data Index: 4888961 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.1602. Min Act: -0.1700
Data Index: 1617321 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.1602. Min Act: -0.1700
Data Index: 7923636 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.1289. Min Act: -0.1700
Data Index: 6848945 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.1289. Min Act: -0.1700
Data Index: 653891 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.1289. Min Act: -0.1700
Data Index: 5520168 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.1289. Min Act: -0.1700
Data Index: 2159691 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.1289. Min Act: -0.1700
Data Index: 7502920 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.0664. Min Act: -0.1700
Data Index: 2263209 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.0352. Min Act: -0.1700
Data Index: 786086 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5664. Min Range: -5.5664
Max Act: 5.0664. Min Act: -0.1700
Data Index: 991016 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19