Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4952 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0743. Min Range: -3.0743
Max Act: 3.0743. Min Act: -0.1700
Data Index: 7041842 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0743. Min Range: -3.0743
Max Act: 3.0270. Min Act: -0.1700
Data Index: 6828127 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0743. Min Range: -3.0743
Max Act: 3.0112. Min Act: -0.1700
Data Index: 1785797 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0743. Min Range: -3.0743
Max Act: 3.0270. Min Act: -0.1700
Data Index: 1725593 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0743. Min Range: -3.0743
Max Act: 2.9954. Min Act: -0.1700
Data Index: 5248827 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0743. Min Range: -3.0743
Max Act: 2.9796. Min Act: -0.1700
Data Index: 3924519 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0743. Min Range: -3.0743
Max Act: 2.9479. Min Act: -0.1700
Data Index: 4211310 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0743. Min Range: -3.0743
Max Act: 2.9321. Min Act: -0.1700
Data Index: 3680053 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0743. Min Range: -3.0743
Max Act: 2.8686. Min Act: -0.1700
Data Index: 2896733 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0743. Min Range: -3.0743
Max Act: 2.8528. Min Act: -0.1700
Data Index: 530241 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0743. Min Range: -3.0743
Max Act: 2.8528. Min Act: -0.1700
Data Index: 7502122 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0743. Min Range: -3.0743
Max Act: 2.8369. Min Act: -0.1700
Data Index: 1335711 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0743. Min Range: -3.0743
Max Act: 2.8369. Min Act: -0.1700
Data Index: 3260280 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0743. Min Range: -3.0743
Max Act: 2.8369. Min Act: -0.1700
Data Index: 3135877 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0743. Min Range: -3.0743
Max Act: 2.8051. Min Act: -0.1700
Data Index: 7053801 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0743. Min Range: -3.0743
Max Act: 2.8210. Min Act: -0.1700
Data Index: 6779717 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0743. Min Range: -3.0743
Max Act: 2.8051. Min Act: -0.1700
Data Index: 225409 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0743. Min Range: -3.0743
Max Act: 2.8051. Min Act: -0.1700
Data Index: 3916817 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0743. Min Range: -3.0743
Max Act: 2.8051. Min Act: -0.1700
Data Index: 6946253 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0743. Min Range: -3.0743
Max Act: 2.7732. Min Act: -0.1700
Data Index: 5729862 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19