Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3662 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.3092. Min Act: -0.1700
Data Index: 1960581 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.2779. Min Act: -0.1700
Data Index: 5744485 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.2467. Min Act: -0.1700
Data Index: 5401454 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.1842. Min Act: -0.1700
Data Index: 4576124 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.1529. Min Act: -0.1700
Data Index: 4680578 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.1217. Min Act: -0.1700
Data Index: 1735214 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.1217. Min Act: -0.1700
Data Index: 4250605 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.0904. Min Act: -0.1700
Data Index: 4985370 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.0904. Min Act: -0.1700
Data Index: 6276708 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.0592. Min Act: -0.1700
Data Index: 806943 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.0592. Min Act: -0.1700
Data Index: 4274214 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.0592. Min Act: -0.1700
Data Index: 3373032 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.0592. Min Act: -0.1700
Data Index: 1003997 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.0279. Min Act: -0.1700
Data Index: 8005216 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.0279. Min Act: -0.1700
Data Index: 7607712 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.0279. Min Act: -0.1700
Data Index: 8534619 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3092. Min Range: -6.3092
Max Act: 5.9967. Min Act: -0.1700
Data Index: 8465638 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3092. Min Range: -6.3092
Max Act: 5.9654. Min Act: -0.1700
Data Index: 829715 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3092. Min Range: -6.3092
Max Act: 5.9967. Min Act: -0.1700
Data Index: 7972064 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3092. Min Range: -6.3092
Max Act: 5.9654. Min Act: -0.1700
Data Index: 7971037 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19