Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4437 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.4915. Min Act: -0.1700
Data Index: 2042363 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.3353. Min Act: -0.1700
Data Index: 3610599 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.3353. Min Act: -0.1700
Data Index: 5231544 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.3040. Min Act: -0.1700
Data Index: 13161 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.3040. Min Act: -0.1700
Data Index: 994629 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.2728. Min Act: -0.1700
Data Index: 5377711 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.2728. Min Act: -0.1700
Data Index: 3610602 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.2728. Min Act: -0.1700
Data Index: 2556692 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.2415. Min Act: -0.1700
Data Index: 7768867 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.2415. Min Act: -0.1700
Data Index: 6590541 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.2415. Min Act: -0.1700
Data Index: 2307146 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.1790. Min Act: -0.1700
Data Index: 2385792 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.1790. Min Act: -0.1700
Data Index: 1183209 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.1790. Min Act: -0.1700
Data Index: 2556691 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.1478. Min Act: -0.1700
Data Index: 5567713 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.1478. Min Act: -0.1700
Data Index: 6225237 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.1478. Min Act: -0.1700
Data Index: 8824249 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.0852. Min Act: -0.1700
Data Index: 6332719 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.1165. Min Act: -0.1700
Data Index: 1781369 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4915. Min Range: -4.4915
Max Act: 4.1165. Min Act: -0.1700
Data Index: 6013165 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19