Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4961 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.3576. Min Act: -0.1700
Data Index: 7265793 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.2951. Min Act: -0.1700
Data Index: 2849982 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.2951. Min Act: -0.1700
Data Index: 8457386 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.2638. Min Act: -0.1700
Data Index: 5870498 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.2013. Min Act: -0.1700
Data Index: 7246509 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.2013. Min Act: -0.1700
Data Index: 793711 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.2013. Min Act: -0.1700
Data Index: 4377552 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.1701. Min Act: -0.1700
Data Index: 2861529 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.2013. Min Act: -0.1700
Data Index: 4847754 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.1388. Min Act: -0.1700
Data Index: 1952138 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.1388. Min Act: -0.1700
Data Index: 7935637 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.1076. Min Act: -0.1700
Data Index: 1465048 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.1076. Min Act: -0.1700
Data Index: 4034492 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.1076. Min Act: -0.1700
Data Index: 4847753 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.0763. Min Act: -0.1700
Data Index: 5328341 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.0763. Min Act: -0.1700
Data Index: 6584964 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.0451. Min Act: -0.1700
Data Index: 3085894 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.0451. Min Act: -0.1700
Data Index: 583760 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.0451. Min Act: -0.1700
Data Index: 2861528 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3576. Min Range: -5.3576
Max Act: 5.0763. Min Act: -0.1700
Data Index: 7223002 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19