Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2836 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.8331. Min Act: -0.1700
Data Index: 4707106 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.8013. Min Act: -0.1700
Data Index: 975149 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.8013. Min Act: -0.1700
Data Index: 3747440 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.8013. Min Act: -0.1700
Data Index: 8747595 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.8013. Min Act: -0.1700
Data Index: 8577007 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.7854. Min Act: -0.1700
Data Index: 8747593 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.7854. Min Act: -0.1700
Data Index: 2733016 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.7854. Min Act: -0.1700
Data Index: 5247184 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.7694. Min Act: -0.1700
Data Index: 6960541 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.7694. Min Act: -0.1700
Data Index: 7659330 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.7535. Min Act: -0.1700
Data Index: 6785155 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.7535. Min Act: -0.1700
Data Index: 5678132 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.7535. Min Act: -0.1700
Data Index: 1754249 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.7535. Min Act: -0.1700
Data Index: 4920748 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.7375. Min Act: -0.1700
Data Index: 6996737 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.7375. Min Act: -0.1700
Data Index: 2545445 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.7375. Min Act: -0.1700
Data Index: 4699297 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.7375. Min Act: -0.1700
Data Index: 1692180 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.7375. Min Act: -0.1700
Data Index: 7237186 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8331. Min Range: -2.8331
Max Act: 2.7375. Min Act: -0.1700
Data Index: 7989888 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19