Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3511 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0809. Min Range: -6.0809
Max Act: 6.0809. Min Act: -0.1700
Data Index: 3807367 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.7372. Min Act: -0.1700
Data Index: 672526 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.6747. Min Act: -0.1700
Data Index: 3134022 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.6747. Min Act: -0.1700
Data Index: 4082919 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.6122. Min Act: -0.1700
Data Index: 1085281 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.6122. Min Act: -0.1700
Data Index: 2131407 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.5497. Min Act: -0.1700
Data Index: 120435 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.4559. Min Act: -0.1700
Data Index: 1270184 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.4559. Min Act: -0.1700
Data Index: 3966836 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.4559. Min Act: -0.1700
Data Index: 6267525 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.4559. Min Act: -0.1700
Data Index: 4743265 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.4559. Min Act: -0.1700
Data Index: 5715541 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.4247. Min Act: -0.1700
Data Index: 720845 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.3934. Min Act: -0.1700
Data Index: 4083152 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.3622. Min Act: -0.1700
Data Index: 1374086 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.3622. Min Act: -0.1700
Data Index: 7321216 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.3309. Min Act: -0.1700
Data Index: 598800 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.2997. Min Act: -0.1700
Data Index: 412570 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.3622. Min Act: -0.1700
Data Index: 8791762 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0809. Min Range: -6.0809
Max Act: 5.3309. Min Act: -0.1700
Data Index: 5266232 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19