Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4974 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.7642. Min Act: -0.1700
Data Index: 5612640 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.5767. Min Act: -0.1700
Data Index: 680524 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.5142. Min Act: -0.1700
Data Index: 8013179 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.4517. Min Act: -0.1700
Data Index: 640571 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.4517. Min Act: -0.1700
Data Index: 7612722 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.4205. Min Act: -0.1700
Data Index: 1644520 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.3580. Min Act: -0.1700
Data Index: 851353 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.3892. Min Act: -0.1700
Data Index: 4581606 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.3580. Min Act: -0.1700
Data Index: 8367076 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.3580. Min Act: -0.1700
Data Index: 710841 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.3580. Min Act: -0.1700
Data Index: 1305222 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.3267. Min Act: -0.1700
Data Index: 6201425 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.2955. Min Act: -0.1700
Data Index: 852436 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.2330. Min Act: -0.1700
Data Index: 3370100 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.2017. Min Act: -0.1700
Data Index: 2282653 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.1705. Min Act: -0.1700
Data Index: 6657430 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.1705. Min Act: -0.1700
Data Index: 7767132 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.1705. Min Act: -0.1700
Data Index: 5166799 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.1392. Min Act: -0.1700
Data Index: 7165866 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7642. Min Range: -6.7642
Max Act: 6.1080. Min Act: -0.1700
Data Index: 6432215 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19