Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3251 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.9360. Min Act: -0.1700
Data Index: 8397400 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.8735. Min Act: -0.1700
Data Index: 6957162 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.8110. Min Act: -0.1700
Data Index: 3657777 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.7797. Min Act: -0.1700
Data Index: 7448026 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.8110. Min Act: -0.1700
Data Index: 7542708 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.7797. Min Act: -0.1700
Data Index: 3439618 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.7797. Min Act: -0.1700
Data Index: 4344138 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.7797. Min Act: -0.1700
Data Index: 3241285 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.7172. Min Act: -0.1700
Data Index: 3893699 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.7172. Min Act: -0.1700
Data Index: 670442 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.6859. Min Act: -0.1700
Data Index: 1726298 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.7172. Min Act: -0.1700
Data Index: 4427639 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.6547. Min Act: -0.1700
Data Index: 6189215 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.6234. Min Act: -0.1700
Data Index: 521890 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.6547. Min Act: -0.1700
Data Index: 4950709 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.5609. Min Act: -0.1700
Data Index: 5659257 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.5922. Min Act: -0.1700
Data Index: 5459143 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.5922. Min Act: -0.1700
Data Index: 2885256 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.5922. Min Act: -0.1700
Data Index: 2798832 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9360. Min Range: -4.9360
Max Act: 4.5922. Min Act: -0.1700
Data Index: 4076221 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19