Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4723 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.5492. Min Act: -0.1700
Data Index: 5577107 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.4867. Min Act: -0.1700
Data Index: 6534990 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.4242. Min Act: -0.1700
Data Index: 2441792 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.3929. Min Act: -0.1700
Data Index: 5851758 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.3617. Min Act: -0.1700
Data Index: 665952 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.3617. Min Act: -0.1700
Data Index: 7251869 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.3617. Min Act: -0.1700
Data Index: 2567753 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.3304. Min Act: -0.1700
Data Index: 3717581 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.3304. Min Act: -0.1700
Data Index: 1450342 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.3304. Min Act: -0.1700
Data Index: 4908305 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.2992. Min Act: -0.1700
Data Index: 1397594 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.3304. Min Act: -0.1700
Data Index: 6890538 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.2679. Min Act: -0.1700
Data Index: 2624040 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.2367. Min Act: -0.1700
Data Index: 1106841 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.2367. Min Act: -0.1700
Data Index: 6298313 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.2054. Min Act: -0.1700
Data Index: 8114820 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.2054. Min Act: -0.1700
Data Index: 4391679 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.2054. Min Act: -0.1700
Data Index: 3834026 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.1742. Min Act: -0.1700
Data Index: 924524 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.1742. Min Act: -0.1700
Data Index: 6385262 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19