Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5023 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8076. Min Range: -4.8076
Max Act: 4.8076. Min Act: -0.1700
Data Index: 4173106 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8076. Min Range: -4.8076
Max Act: 4.3701. Min Act: -0.1700
Data Index: 6381871 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8076. Min Range: -4.8076
Max Act: 4.3076. Min Act: -0.1700
Data Index: 6381870 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8076. Min Range: -4.8076
Max Act: 4.2763. Min Act: -0.1700
Data Index: 6381869 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8076. Min Range: -4.8076
Max Act: 4.2138. Min Act: -0.1700
Data Index: 7500577 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8076. Min Range: -4.8076
Max Act: 4.2138. Min Act: -0.1700
Data Index: 2218128 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8076. Min Range: -4.8076
Max Act: 4.1826. Min Act: -0.1700
Data Index: 6381868 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8076. Min Range: -4.8076
Max Act: 4.1513. Min Act: -0.1700
Data Index: 1137228 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8076. Min Range: -4.8076
Max Act: 4.1201. Min Act: -0.1700
Data Index: 6906433 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8076. Min Range: -4.8076
Max Act: 4.0888. Min Act: -0.1700
Data Index: 3187001 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8076. Min Range: -4.8076
Max Act: 4.0888. Min Act: -0.1700
Data Index: 5678368 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8076. Min Range: -4.8076
Max Act: 4.0888. Min Act: -0.1700
Data Index: 6381867 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8076. Min Range: -4.8076
Max Act: 4.0575. Min Act: -0.1700
Data Index: 2637611 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8076. Min Range: -4.8076
Max Act: 4.0575. Min Act: -0.1700
Data Index: 8166218 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8076. Min Range: -4.8076
Max Act: 3.9950. Min Act: -0.1700
Data Index: 6261230 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8076. Min Range: -4.8076
Max Act: 3.9950. Min Act: -0.1700
Data Index: 6802848 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8076. Min Range: -4.8076
Max Act: 3.9950. Min Act: -0.1700
Data Index: 3271565 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8076. Min Range: -4.8076
Max Act: 3.9638. Min Act: -0.1700
Data Index: 3218758 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8076. Min Range: -4.8076
Max Act: 3.9638. Min Act: -0.1700
Data Index: 2637638 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8076. Min Range: -4.8076
Max Act: 3.9325. Min Act: -0.1700
Data Index: 4010234 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19