Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2722 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.7590. Min Act: -0.1700
Data Index: 3665877 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.5715. Min Act: -0.1700
Data Index: 931712 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.4778. Min Act: -0.1700
Data Index: 582862 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.3840. Min Act: -0.1700
Data Index: 4096927 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.3840. Min Act: -0.1700
Data Index: 7587475 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.3215. Min Act: -0.1700
Data Index: 5503223 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.2903. Min Act: -0.1700
Data Index: 7354330 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.2590. Min Act: -0.1700
Data Index: 2743307 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.2278. Min Act: -0.1700
Data Index: 8069930 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.1965. Min Act: -0.1700
Data Index: 6881066 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.2278. Min Act: -0.1700
Data Index: 8236027 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.1965. Min Act: -0.1700
Data Index: 8280539 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.1340. Min Act: -0.1700
Data Index: 4135696 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.1028. Min Act: -0.1700
Data Index: 7913384 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.1340. Min Act: -0.1700
Data Index: 6112822 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.1028. Min Act: -0.1700
Data Index: 2137862 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.1028. Min Act: -0.1700
Data Index: 3626361 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.1028. Min Act: -0.1700
Data Index: 6047931 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.0715. Min Act: -0.1700
Data Index: 5706861 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7590. Min Range: -7.7590
Max Act: 7.0715. Min Act: -0.1700
Data Index: 4940128 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19