Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 72 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2949. Min Range: -8.2949
Max Act: 8.2949. Min Act: -0.1700
Data Index: 8366852 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.7949. Min Act: -0.1700
Data Index: 2299164 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.7949. Min Act: -0.1700
Data Index: 3339336 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.6699. Min Act: -0.1700
Data Index: 5820828 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.6074. Min Act: -0.1700
Data Index: 6409498 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.6074. Min Act: -0.1700
Data Index: 2233883 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.5136. Min Act: -0.1700
Data Index: 1031915 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.5136. Min Act: -0.1700
Data Index: 5907903 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.5136. Min Act: -0.1700
Data Index: 5331399 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.4511. Min Act: -0.1700
Data Index: 8657794 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.4824. Min Act: -0.1700
Data Index: 4123533 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.4824. Min Act: -0.1700
Data Index: 5643304 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.4824. Min Act: -0.1700
Data Index: 2585809 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.4824. Min Act: -0.1700
Data Index: 5088210 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.4511. Min Act: -0.1700
Data Index: 6905536 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.4824. Min Act: -0.1700
Data Index: 203645 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.4199. Min Act: -0.1700
Data Index: 1454036 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.4199. Min Act: -0.1700
Data Index: 7940373 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.3886. Min Act: -0.1700
Data Index: 3034736 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2949. Min Range: -8.2949
Max Act: 7.3886. Min Act: -0.1700
Data Index: 6788255 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19