Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2304 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.9757. Min Act: -0.1700
Data Index: 4511981 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.6007. Min Act: -0.1700
Data Index: 5475293 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.6007. Min Act: -0.1700
Data Index: 1143249 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.5382. Min Act: -0.1700
Data Index: 4598797 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.5382. Min Act: -0.1700
Data Index: 5865118 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.4757. Min Act: -0.1700
Data Index: 3296801 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.4757. Min Act: -0.1700
Data Index: 1275018 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.4132. Min Act: -0.1700
Data Index: 3895076 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.3507. Min Act: -0.1700
Data Index: 5797552 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.3507. Min Act: -0.1700
Data Index: 7123977 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.2882. Min Act: -0.1700
Data Index: 7128606 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.2257. Min Act: -0.1700
Data Index: 2676903 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.1632. Min Act: -0.1700
Data Index: 7821733 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.1632. Min Act: -0.1700
Data Index: 5068939 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.1632. Min Act: -0.1700
Data Index: 3148589 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.1007. Min Act: -0.1700
Data Index: 3132207 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.1007. Min Act: -0.1700
Data Index: 2282211 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.1007. Min Act: -0.1700
Data Index: 5448568 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.1007. Min Act: -0.1700
Data Index: 4401415 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9757. Min Range: -8.9757
Max Act: 8.1007. Min Act: -0.1700
Data Index: 5948511 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19