Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5334 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4652. Min Range: -5.4652
Max Act: 5.4652. Min Act: -0.1700
Data Index: 5094952 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.9027. Min Act: -0.1700
Data Index: 326350 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.8715. Min Act: -0.1700
Data Index: 6948331 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.8715. Min Act: -0.1700
Data Index: 8339970 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.8402. Min Act: -0.1700
Data Index: 4214034 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.8402. Min Act: -0.1700
Data Index: 7474365 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.7777. Min Act: -0.1699
Data Index: 7680965 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.8090. Min Act: -0.1700
Data Index: 6545712 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.8090. Min Act: -0.1700
Data Index: 1254640 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.7777. Min Act: -0.1700
Data Index: 5290792 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.7777. Min Act: -0.1700
Data Index: 5803728 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.8090. Min Act: -0.1700
Data Index: 6194907 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.7777. Min Act: -0.1700
Data Index: 13895 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.7465. Min Act: -0.1700
Data Index: 1084395 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.7465. Min Act: -0.1700
Data Index: 2821501 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.7465. Min Act: -0.1700
Data Index: 8030035 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.7465. Min Act: -0.1700
Data Index: 4688803 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.7465. Min Act: -0.1700
Data Index: 4479078 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.7152. Min Act: -0.1700
Data Index: 6219206 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4652. Min Range: -5.4652
Max Act: 4.7152. Min Act: -0.1700
Data Index: 6654993 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19