Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1199 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3244. Min Range: -8.3244
Max Act: 8.3244. Min Act: -0.1700
Data Index: 637989 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3244. Min Range: -8.3244
Max Act: 8.1369. Min Act: -0.1700
Data Index: 120328 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3244. Min Range: -8.3244
Max Act: 8.0744. Min Act: -0.1700
Data Index: 8617526 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3244. Min Range: -8.3244
Max Act: 8.0119. Min Act: -0.1700
Data Index: 3074673 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3244. Min Range: -8.3244
Max Act: 7.9494. Min Act: -0.1700
Data Index: 8313351 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3244. Min Range: -8.3244
Max Act: 7.9494. Min Act: -0.1700
Data Index: 335347 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3244. Min Range: -8.3244
Max Act: 7.9494. Min Act: -0.1700
Data Index: 7757624 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3244. Min Range: -8.3244
Max Act: 7.8869. Min Act: -0.1700
Data Index: 6007161 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3244. Min Range: -8.3244
Max Act: 7.8869. Min Act: -0.1700
Data Index: 3296543 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3244. Min Range: -8.3244
Max Act: 7.8244. Min Act: -0.1700
Data Index: 5853684 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3244. Min Range: -8.3244
Max Act: 7.7619. Min Act: -0.1700
Data Index: 8686698 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3244. Min Range: -8.3244
Max Act: 7.7619. Min Act: -0.1700
Data Index: 5147522 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3244. Min Range: -8.3244
Max Act: 7.7619. Min Act: -0.1700
Data Index: 934681 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3244. Min Range: -8.3244
Max Act: 7.6994. Min Act: -0.1700
Data Index: 5624843 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3244. Min Range: -8.3244
Max Act: 7.6994. Min Act: -0.1700
Data Index: 3277260 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3244. Min Range: -8.3244
Max Act: 7.6994. Min Act: -0.1700
Data Index: 8235372 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3244. Min Range: -8.3244
Max Act: 7.6994. Min Act: -0.1700
Data Index: 4017546 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3244. Min Range: -8.3244
Max Act: 7.6369. Min Act: -0.1700
Data Index: 1255818 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3244. Min Range: -8.3244
Max Act: 7.6369. Min Act: -0.1700
Data Index: 287835 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3244. Min Range: -8.3244
Max Act: 7.6369. Min Act: -0.1700
Data Index: 8235371 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19