Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8702. Min Range: -8.8702
Max Act: 8.8702. Min Act: -0.1700
Data Index: 410161 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8702. Min Range: -8.8702
Max Act: 8.8702. Min Act: -0.1700
Data Index: 7824512 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8702. Min Range: -8.8702
Max Act: 8.5577. Min Act: -0.1700
Data Index: 6992063 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8702. Min Range: -8.8702
Max Act: 8.4952. Min Act: -0.1700
Data Index: 4256733 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8702. Min Range: -8.8702
Max Act: 8.3702. Min Act: -0.1700
Data Index: 8370216 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8702. Min Range: -8.8702
Max Act: 8.3702. Min Act: -0.1700
Data Index: 1469750 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8702. Min Range: -8.8702
Max Act: 8.3077. Min Act: -0.1700
Data Index: 1237602 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8702. Min Range: -8.8702
Max Act: 8.1827. Min Act: -0.1700
Data Index: 5322852 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8702. Min Range: -8.8702
Max Act: 8.2452. Min Act: -0.1700
Data Index: 3921040 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8702. Min Range: -8.8702
Max Act: 8.1202. Min Act: -0.1700
Data Index: 8624485 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8702. Min Range: -8.8702
Max Act: 8.1202. Min Act: -0.1700
Data Index: 5103817 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8702. Min Range: -8.8702
Max Act: 8.0577. Min Act: -0.1700
Data Index: 8806839 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8702. Min Range: -8.8702
Max Act: 8.0577. Min Act: -0.1700
Data Index: 8665388 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8702. Min Range: -8.8702
Max Act: 7.9640. Min Act: -0.1700
Data Index: 8194900 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8702. Min Range: -8.8702
Max Act: 7.9015. Min Act: -0.1700
Data Index: 1244105 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8702. Min Range: -8.8702
Max Act: 7.9327. Min Act: -0.1700
Data Index: 1799901 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8702. Min Range: -8.8702
Max Act: 7.9015. Min Act: -0.1700
Data Index: 8580193 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8702. Min Range: -8.8702
Max Act: 7.9327. Min Act: -0.1700
Data Index: 3862299 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8702. Min Range: -8.8702
Max Act: 7.9015. Min Act: -0.1700
Data Index: 3050415 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8702. Min Range: -8.8702
Max Act: 7.8702. Min Act: -0.1700
Data Index: 3751277 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19