Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.8172. Min Act: -0.1700
Data Index: 984215 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.6922. Min Act: -0.1700
Data Index: 4335905 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.6297. Min Act: -0.1700
Data Index: 990539 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.6297. Min Act: -0.1700
Data Index: 794574 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.5360. Min Act: -0.1700
Data Index: 7259 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.5672. Min Act: -0.1700
Data Index: 1998067 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.5672. Min Act: -0.1700
Data Index: 8317531 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.5360. Min Act: -0.1700
Data Index: 1415739 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.5672. Min Act: -0.1700
Data Index: 2076481 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.5360. Min Act: -0.1700
Data Index: 7671257 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.5047. Min Act: -0.1700
Data Index: 5181197 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.4735. Min Act: -0.1700
Data Index: 8520961 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.4735. Min Act: -0.1700
Data Index: 5815478 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.4735. Min Act: -0.1700
Data Index: 3089166 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.4422. Min Act: -0.1700
Data Index: 4618284 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.4110. Min Act: -0.1700
Data Index: 6658576 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.4110. Min Act: -0.1700
Data Index: 2544801 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.3797. Min Act: -0.1700
Data Index: 551362 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.4110. Min Act: -0.1700
Data Index: 4904282 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8172. Min Range: -7.8172
Max Act: 7.4110. Min Act: -0.1700
Data Index: 5584120 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19