Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5871 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3356. Min Range: -4.3356
Max Act: 4.3043. Min Act: -0.1700
Data Index: 4042725 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3356. Min Range: -4.3356
Max Act: 4.3356. Min Act: -0.1700
Data Index: 4633269 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3356. Min Range: -4.3356
Max Act: 4.3356. Min Act: -0.1700
Data Index: 8195217 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3356. Min Range: -4.3356
Max Act: 4.3043. Min Act: -0.1700
Data Index: 2963261 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3356. Min Range: -4.3356
Max Act: 4.3043. Min Act: -0.1700
Data Index: 565409 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3356. Min Range: -4.3356
Max Act: 4.2418. Min Act: -0.1700
Data Index: 8192535 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3356. Min Range: -4.3356
Max Act: 4.1168. Min Act: -0.1700
Data Index: 6458785 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3356. Min Range: -4.3356
Max Act: 4.0856. Min Act: -0.1700
Data Index: 7322043 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3356. Min Range: -4.3356
Max Act: 4.0543. Min Act: -0.1700
Data Index: 872244 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3356. Min Range: -4.3356
Max Act: 4.0230. Min Act: -0.1700
Data Index: 8745199 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3356. Min Range: -4.3356
Max Act: 3.9918. Min Act: -0.1700
Data Index: 2006047 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3356. Min Range: -4.3356
Max Act: 3.9605. Min Act: -0.1700
Data Index: 6456482 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3356. Min Range: -4.3356
Max Act: 3.9918. Min Act: -0.1700
Data Index: 5846515 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3356. Min Range: -4.3356
Max Act: 3.9918. Min Act: -0.1700
Data Index: 3086657 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3356. Min Range: -4.3356
Max Act: 3.9293. Min Act: -0.1700
Data Index: 2925685 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3356. Min Range: -4.3356
Max Act: 3.9293. Min Act: -0.1700
Data Index: 2332115 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3356. Min Range: -4.3356
Max Act: 3.8980. Min Act: -0.1700
Data Index: 6097582 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3356. Min Range: -4.3356
Max Act: 3.8980. Min Act: -0.1700
Data Index: 4825105 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3356. Min Range: -4.3356
Max Act: 3.8980. Min Act: -0.1700
Data Index: 74851 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3356. Min Range: -4.3356
Max Act: 3.8980. Min Act: -0.1700
Data Index: 8654000 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19