Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3375 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.9485. Min Act: -0.1700
Data Index: 2582042 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.7923. Min Act: -0.1700
Data Index: 4297507 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.7923. Min Act: -0.1700
Data Index: 3423369 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.7298. Min Act: -0.1700
Data Index: 1830953 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.7298. Min Act: -0.1700
Data Index: 7785806 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.7610. Min Act: -0.1700
Data Index: 1379419 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.7298. Min Act: -0.1700
Data Index: 6680376 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.7298. Min Act: -0.1700
Data Index: 8534826 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.6985. Min Act: -0.1700
Data Index: 5057952 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.6673. Min Act: -0.1700
Data Index: 3924298 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.6673. Min Act: -0.1700
Data Index: 4643764 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.6985. Min Act: -0.1700
Data Index: 1161788 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.6673. Min Act: -0.1700
Data Index: 6686587 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.6673. Min Act: -0.1700
Data Index: 5959516 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.6360. Min Act: -0.1700
Data Index: 4502664 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.5735. Min Act: -0.1700
Data Index: 5664537 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.5735. Min Act: -0.1700
Data Index: 1692289 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.5735. Min Act: -0.1700
Data Index: 525060 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.5735. Min Act: -0.1700
Data Index: 5223917 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9485. Min Range: -5.9485
Max Act: 5.5110. Min Act: -0.1700
Data Index: 756925 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19