Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 306 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2196. Min Range: -7.2196
Max Act: 7.2196. Min Act: -0.1700
Data Index: 2798259 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2196. Min Range: -7.2196
Max Act: 7.0946. Min Act: -0.1700
Data Index: 6305321 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2196. Min Range: -7.2196
Max Act: 7.0009. Min Act: -0.1700
Data Index: 4008103 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2196. Min Range: -7.2196
Max Act: 6.9696. Min Act: -0.1700
Data Index: 219546 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2196. Min Range: -7.2196
Max Act: 6.9071. Min Act: -0.1700
Data Index: 3699487 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2196. Min Range: -7.2196
Max Act: 6.8446. Min Act: -0.1700
Data Index: 3065918 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2196. Min Range: -7.2196
Max Act: 6.8134. Min Act: -0.1700
Data Index: 3757580 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2196. Min Range: -7.2196
Max Act: 6.7821. Min Act: -0.1700
Data Index: 6383545 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2196. Min Range: -7.2196
Max Act: 6.7196. Min Act: -0.1700
Data Index: 7199309 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2196. Min Range: -7.2196
Max Act: 6.7196. Min Act: -0.1700
Data Index: 2409343 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2196. Min Range: -7.2196
Max Act: 6.7196. Min Act: -0.1700
Data Index: 6286251 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2196. Min Range: -7.2196
Max Act: 6.6884. Min Act: -0.1700
Data Index: 203308 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2196. Min Range: -7.2196
Max Act: 6.7196. Min Act: -0.1700
Data Index: 5763832 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2196. Min Range: -7.2196
Max Act: 6.7196. Min Act: -0.1700
Data Index: 5688304 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2196. Min Range: -7.2196
Max Act: 6.6884. Min Act: -0.1700
Data Index: 3171798 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2196. Min Range: -7.2196
Max Act: 6.6571. Min Act: -0.1700
Data Index: 4957981 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2196. Min Range: -7.2196
Max Act: 6.5946. Min Act: -0.1700
Data Index: 120375 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2196. Min Range: -7.2196
Max Act: 6.5946. Min Act: -0.1700
Data Index: 5320957 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2196. Min Range: -7.2196
Max Act: 6.6259. Min Act: -0.1700
Data Index: 7288716 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2196. Min Range: -7.2196
Max Act: 6.5946. Min Act: -0.1700
Data Index: 8666872 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19