Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2345 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0285. Min Range: -4.0285
Max Act: 4.0285. Min Act: -0.1700
Data Index: 8518315 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0285. Min Range: -4.0285
Max Act: 4.0285. Min Act: -0.1700
Data Index: 7672869 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9660. Min Act: -0.1700
Data Index: 909501 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9347. Min Act: -0.1700
Data Index: 5913571 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9035. Min Act: -0.1700
Data Index: 2847045 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9035. Min Act: -0.1700
Data Index: 1504610 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.8409. Min Act: -0.1700
Data Index: 2969315 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.8722. Min Act: -0.1700
Data Index: 2455804 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.8722. Min Act: -0.1700
Data Index: 1417075 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.8409. Min Act: -0.1700
Data Index: 7605916 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.8097. Min Act: -0.1700
Data Index: 8832925 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.8097. Min Act: -0.1700
Data Index: 4221145 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.8097. Min Act: -0.1700
Data Index: 61213 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.8097. Min Act: -0.1700
Data Index: 5562925 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.8097. Min Act: -0.1700
Data Index: 6744169 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.8097. Min Act: -0.1700
Data Index: 231481 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.7784. Min Act: -0.1700
Data Index: 6787281 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.7940. Min Act: -0.1700
Data Index: 8174536 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.7940. Min Act: -0.1700
Data Index: 3113540 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.7784. Min Act: -0.1700
Data Index: 4054688 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19