Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2702 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.8894. Min Act: -0.1700
Data Index: 5493306 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.8581. Min Act: -0.1700
Data Index: 8056382 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.7956. Min Act: -0.1700
Data Index: 5803889 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.6394. Min Act: -0.1700
Data Index: 727921 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.5456. Min Act: -0.1700
Data Index: 7726160 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.5769. Min Act: -0.1700
Data Index: 2639585 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.5456. Min Act: -0.1700
Data Index: 7960123 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.4831. Min Act: -0.1700
Data Index: 2500769 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.4831. Min Act: -0.1700
Data Index: 7733387 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.4831. Min Act: -0.1700
Data Index: 1832600 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.4831. Min Act: -0.1700
Data Index: 545043 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.4519. Min Act: -0.1700
Data Index: 3938341 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.3894. Min Act: -0.1700
Data Index: 5803888 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.4206. Min Act: -0.1700
Data Index: 2468241 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.4206. Min Act: -0.1700
Data Index: 7917472 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.4206. Min Act: -0.1700
Data Index: 7820172 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.4519. Min Act: -0.1700
Data Index: 177194 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.4206. Min Act: -0.1700
Data Index: 6681756 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.4206. Min Act: -0.1700
Data Index: 6344776 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8894. Min Range: -5.8894
Max Act: 5.3894. Min Act: -0.1700
Data Index: 4553048 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19