Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3164 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.8693. Min Act: -0.1700
Data Index: 4950408 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.8693. Min Act: -0.1700
Data Index: 1075663 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.7756. Min Act: -0.1700
Data Index: 8313999 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.7756. Min Act: -0.1700
Data Index: 7724473 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.7131. Min Act: -0.1700
Data Index: 7170639 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.6818. Min Act: -0.1700
Data Index: 2128185 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.6818. Min Act: -0.1700
Data Index: 1241276 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.6818. Min Act: -0.1700
Data Index: 3118178 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.6506. Min Act: -0.1700
Data Index: 2703001 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.6818. Min Act: -0.1700
Data Index: 8442851 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.6193. Min Act: -0.1700
Data Index: 5490614 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.6193. Min Act: -0.1700
Data Index: 4487766 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.5881. Min Act: -0.1700
Data Index: 6035169 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.5881. Min Act: -0.1700
Data Index: 5393981 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.5256. Min Act: -0.1700
Data Index: 1862618 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.5568. Min Act: -0.1700
Data Index: 2389708 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.5568. Min Act: -0.1700
Data Index: 8050393 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.5568. Min Act: -0.1700
Data Index: 5566850 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.5256. Min Act: -0.1700
Data Index: 7205458 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8693. Min Range: -4.8693
Max Act: 4.4943. Min Act: -0.1700
Data Index: 4409041 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19