Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4147 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.3735. Min Act: -0.1700
Data Index: 5220777 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.3110. Min Act: -0.1700
Data Index: 511164 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.2798. Min Act: -0.1700
Data Index: 103944 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.2798. Min Act: -0.1700
Data Index: 8721028 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.2485. Min Act: -0.1700
Data Index: 6728196 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.2173. Min Act: -0.1700
Data Index: 6728195 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.1860. Min Act: -0.1700
Data Index: 1222810 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.1548. Min Act: -0.1700
Data Index: 2622600 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.1235. Min Act: -0.1700
Data Index: 3350031 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.0923. Min Act: -0.1700
Data Index: 270583 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.0298. Min Act: -0.1700
Data Index: 7207621 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.0610. Min Act: -0.1700
Data Index: 5925988 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.0298. Min Act: -0.1700
Data Index: 7595437 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.0298. Min Act: -0.1700
Data Index: 5834849 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.9985. Min Act: -0.1700
Data Index: 6888413 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.0298. Min Act: -0.1700
Data Index: 4623432 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.9985. Min Act: -0.1700
Data Index: 3134585 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.9985. Min Act: -0.1700
Data Index: 5617714 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.9985. Min Act: -0.1700
Data Index: 1323270 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.0298. Min Act: -0.1700
Data Index: 6979342 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19