Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4123 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1906. Min Range: -5.1906
Max Act: 5.1906. Min Act: -0.1700
Data Index: 1265576 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1906. Min Range: -5.1906
Max Act: 5.0031. Min Act: -0.1700
Data Index: 1437421 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.9718. Min Act: -0.1700
Data Index: 7768309 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.9406. Min Act: -0.1700
Data Index: 711556 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.9406. Min Act: -0.1700
Data Index: 1442859 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.8781. Min Act: -0.1700
Data Index: 2579333 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.8781. Min Act: -0.1700
Data Index: 1303775 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.8468. Min Act: -0.1700
Data Index: 6074151 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.8468. Min Act: -0.1700
Data Index: 2411672 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.7843. Min Act: -0.1700
Data Index: 2116636 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.7843. Min Act: -0.1700
Data Index: 4609170 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.7843. Min Act: -0.1700
Data Index: 8526995 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.7531. Min Act: -0.1700
Data Index: 3993395 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.7531. Min Act: -0.1700
Data Index: 453401 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.7531. Min Act: -0.1700
Data Index: 8627403 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.7218. Min Act: -0.1700
Data Index: 4300162 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.7218. Min Act: -0.1700
Data Index: 5532138 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.6906. Min Act: -0.1700
Data Index: 93750 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.6906. Min Act: -0.1700
Data Index: 5622739 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.6906. Min Act: -0.1700
Data Index: 1444910 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19