Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3532 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.3135. Min Act: -0.1700
Data Index: 4008191 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.3135. Min Act: -0.1700
Data Index: 4675599 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.2510. Min Act: -0.1700
Data Index: 5302335 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.1885. Min Act: -0.1700
Data Index: 8372738 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.1885. Min Act: -0.1700
Data Index: 1388855 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.1573. Min Act: -0.1700
Data Index: 7059068 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.1573. Min Act: -0.1700
Data Index: 2562716 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.1573. Min Act: -0.1700
Data Index: 5682964 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.1260. Min Act: -0.1700
Data Index: 7286226 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.0948. Min Act: -0.1700
Data Index: 4396421 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.1260. Min Act: -0.1700
Data Index: 3568217 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.1260. Min Act: -0.1700
Data Index: 2661862 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.0635. Min Act: -0.1700
Data Index: 7200040 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.0323. Min Act: -0.1700
Data Index: 6960716 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.0323. Min Act: -0.1700
Data Index: 5271497 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.0323. Min Act: -0.1700
Data Index: 1694841 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.0323. Min Act: -0.1700
Data Index: 8008873 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.0323. Min Act: -0.1700
Data Index: 5775388 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.0323. Min Act: -0.1700
Data Index: 3698364 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3135. Min Range: -5.3135
Max Act: 5.0010. Min Act: -0.1700
Data Index: 933847 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19