Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 898 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.6423. Min Act: -0.1700
Data Index: 5841180 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.5173. Min Act: -0.1700
Data Index: 4435679 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.2360. Min Act: -0.1700
Data Index: 8586378 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.1735. Min Act: -0.1700
Data Index: 4115609 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.1110. Min Act: -0.1700
Data Index: 2047246 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.0798. Min Act: -0.1700
Data Index: 1557065 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.0485. Min Act: -0.1700
Data Index: 3772394 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.0173. Min Act: -0.1700
Data Index: 2303344 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6423. Min Range: -5.6423
Max Act: 4.9860. Min Act: -0.1700
Data Index: 3650788 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6423. Min Range: -5.6423
Max Act: 4.9860. Min Act: -0.1700
Data Index: 3724379 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6423. Min Range: -5.6423
Max Act: 4.9860. Min Act: -0.1700
Data Index: 4987099 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6423. Min Range: -5.6423
Max Act: 4.9860. Min Act: -0.1700
Data Index: 7093912 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6423. Min Range: -5.6423
Max Act: 4.9860. Min Act: -0.1700
Data Index: 5260634 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6423. Min Range: -5.6423
Max Act: 4.9548. Min Act: -0.1700
Data Index: 3494027 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6423. Min Range: -5.6423
Max Act: 4.9548. Min Act: -0.1700
Data Index: 1607194 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6423. Min Range: -5.6423
Max Act: 4.9235. Min Act: -0.1700
Data Index: 2669237 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6423. Min Range: -5.6423
Max Act: 4.9235. Min Act: -0.1700
Data Index: 3794662 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6423. Min Range: -5.6423
Max Act: 4.9235. Min Act: -0.1700
Data Index: 5337836 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6423. Min Range: -5.6423
Max Act: 4.9235. Min Act: -0.1700
Data Index: 1131827 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6423. Min Range: -5.6423
Max Act: 4.9235. Min Act: -0.1700
Data Index: 2320977 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19