Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5164 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.5254. Min Act: -0.1700
Data Index: 546019 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.4941. Min Act: -0.1700
Data Index: 423959 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.4004. Min Act: -0.1700
Data Index: 3969285 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.2129. Min Act: -0.1700
Data Index: 2766556 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.2129. Min Act: -0.1700
Data Index: 5391739 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.2129. Min Act: -0.1700
Data Index: 5171562 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.1816. Min Act: -0.1700
Data Index: 34396 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.1816. Min Act: -0.1700
Data Index: 5224353 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.1816. Min Act: -0.1700
Data Index: 6370979 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.1816. Min Act: -0.1700
Data Index: 6453194 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.1816. Min Act: -0.1700
Data Index: 5471241 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.1504. Min Act: -0.1700
Data Index: 8534687 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.1191. Min Act: -0.1700
Data Index: 3574179 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.1191. Min Act: -0.1700
Data Index: 8749484 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.0879. Min Act: -0.1700
Data Index: 325978 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.1191. Min Act: -0.1700
Data Index: 1346251 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.0566. Min Act: -0.1700
Data Index: 1245924 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.0879. Min Act: -0.1700
Data Index: 8698699 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.0566. Min Act: -0.1700
Data Index: 5600369 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5254. Min Range: -5.5254
Max Act: 5.0566. Min Act: -0.1700
Data Index: 5982485 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19