Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5380 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3672. Min Range: -9.3672
Max Act: 9.3672. Min Act: -0.1700
Data Index: 2841305 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3672. Min Range: -9.3672
Max Act: 9.1797. Min Act: -0.1700
Data Index: 3429271 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3672. Min Range: -9.3672
Max Act: 8.9922. Min Act: -0.1700
Data Index: 4154314 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3672. Min Range: -9.3672
Max Act: 8.9297. Min Act: -0.1700
Data Index: 3599070 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3672. Min Range: -9.3672
Max Act: 8.9297. Min Act: -0.1700
Data Index: 2199028 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3672. Min Range: -9.3672
Max Act: 8.9297. Min Act: -0.1700
Data Index: 2028357 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3672. Min Range: -9.3672
Max Act: 8.8047. Min Act: -0.1700
Data Index: 3599069 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3672. Min Range: -9.3672
Max Act: 8.7422. Min Act: -0.1700
Data Index: 2124624 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3672. Min Range: -9.3672
Max Act: 8.6797. Min Act: -0.1700
Data Index: 342777 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3672. Min Range: -9.3672
Max Act: 8.6172. Min Act: -0.1700
Data Index: 5207388 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3672. Min Range: -9.3672
Max Act: 8.6172. Min Act: -0.1700
Data Index: 1341937 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3672. Min Range: -9.3672
Max Act: 8.5547. Min Act: -0.1700
Data Index: 149975 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3672. Min Range: -9.3672
Max Act: 8.4922. Min Act: -0.1700
Data Index: 819768 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3672. Min Range: -9.3672
Max Act: 8.4922. Min Act: -0.1700
Data Index: 5718639 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3672. Min Range: -9.3672
Max Act: 8.4922. Min Act: -0.1700
Data Index: 2741241 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3672. Min Range: -9.3672
Max Act: 8.4297. Min Act: -0.1700
Data Index: 3808400 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3672. Min Range: -9.3672
Max Act: 8.4297. Min Act: -0.1700
Data Index: 2215266 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3672. Min Range: -9.3672
Max Act: 8.3672. Min Act: -0.1700
Data Index: 5330891 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3672. Min Range: -9.3672
Max Act: 8.3672. Min Act: -0.1700
Data Index: 3249906 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3672. Min Range: -9.3672
Max Act: 8.3672. Min Act: -0.1700
Data Index: 3599067 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19