Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1713 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.4840. Min Act: -0.1700
Data Index: 128352 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.4840. Min Act: -0.1700
Data Index: 3947761 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.4215. Min Act: -0.1700
Data Index: 6951820 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.3590. Min Act: -0.1700
Data Index: 4157182 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.2340. Min Act: -0.1700
Data Index: 3414720 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.2340. Min Act: -0.1700
Data Index: 6149360 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.2340. Min Act: -0.1700
Data Index: 2845521 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.1715. Min Act: -0.1700
Data Index: 7775050 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.1090. Min Act: -0.1700
Data Index: 6619067 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.1090. Min Act: -0.1700
Data Index: 7142358 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.0465. Min Act: -0.1700
Data Index: 6198098 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.0465. Min Act: -0.1700
Data Index: 5534009 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.0465. Min Act: -0.1700
Data Index: 10368 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.0465. Min Act: -0.1700
Data Index: 3038489 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.9215. Min Act: -0.1700
Data Index: 5297154 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.9215. Min Act: -0.1700
Data Index: 6163243 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.7965. Min Act: -0.1700
Data Index: 5787074 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.7965. Min Act: -0.1700
Data Index: 8772460 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.7965. Min Act: -0.1700
Data Index: 6126083 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.8590. Min Act: -0.1700
Data Index: 4468273 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19