Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7827. Min Range: -8.7827
Max Act: 8.7827. Min Act: -0.1700
Data Index: 4213532 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7827. Min Range: -8.7827
Max Act: 8.4702. Min Act: -0.1700
Data Index: 8471550 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7827. Min Range: -8.7827
Max Act: 8.2827. Min Act: -0.1700
Data Index: 3473537 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7827. Min Range: -8.7827
Max Act: 8.2827. Min Act: -0.1700
Data Index: 172143 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7827. Min Range: -8.7827
Max Act: 8.2202. Min Act: -0.1700
Data Index: 1636789 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7827. Min Range: -8.7827
Max Act: 8.0952. Min Act: -0.1700
Data Index: 5574854 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7827. Min Range: -8.7827
Max Act: 7.9702. Min Act: -0.1700
Data Index: 5574853 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7827. Min Range: -8.7827
Max Act: 7.9702. Min Act: -0.1700
Data Index: 5713358 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7827. Min Range: -8.7827
Max Act: 7.9702. Min Act: -0.1700
Data Index: 2852465 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7827. Min Range: -8.7827
Max Act: 7.9702. Min Act: -0.1700
Data Index: 1334079 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7827. Min Range: -8.7827
Max Act: 7.9702. Min Act: -0.1700
Data Index: 374219 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7827. Min Range: -8.7827
Max Act: 7.9077. Min Act: -0.1700
Data Index: 4026560 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7827. Min Range: -8.7827
Max Act: 7.9077. Min Act: -0.1700
Data Index: 7946557 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7827. Min Range: -8.7827
Max Act: 7.9077. Min Act: -0.1700
Data Index: 977013 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7827. Min Range: -8.7827
Max Act: 7.8452. Min Act: -0.1700
Data Index: 7193913 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7827. Min Range: -8.7827
Max Act: 7.8452. Min Act: -0.1700
Data Index: 3249967 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7827. Min Range: -8.7827
Max Act: 7.8452. Min Act: -0.1700
Data Index: 8484777 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7827. Min Range: -8.7827
Max Act: 7.8452. Min Act: -0.1700
Data Index: 4670828 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7827. Min Range: -8.7827
Max Act: 7.7827. Min Act: -0.1700
Data Index: 1062362 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7827. Min Range: -8.7827
Max Act: 7.7827. Min Act: -0.1700
Data Index: 818831 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19