Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3074 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.9178. Min Act: -0.1700
Data Index: 3452939 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.8240. Min Act: -0.1700
Data Index: 4411691 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.7928. Min Act: -0.1700
Data Index: 5168939 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.7615. Min Act: -0.1700
Data Index: 7202790 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.7615. Min Act: -0.1700
Data Index: 2899629 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.7615. Min Act: -0.1700
Data Index: 3838378 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.7303. Min Act: -0.1700
Data Index: 7304028 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.6990. Min Act: -0.1700
Data Index: 4156287 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.7303. Min Act: -0.1700
Data Index: 7011871 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.7303. Min Act: -0.1700
Data Index: 7304038 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.6990. Min Act: -0.1700
Data Index: 6975025 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.6678. Min Act: -0.1700
Data Index: 8264945 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.6678. Min Act: -0.1700
Data Index: 5696723 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.6990. Min Act: -0.1700
Data Index: 1422553 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.6678. Min Act: -0.1700
Data Index: 3931424 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.6678. Min Act: -0.1700
Data Index: 7806351 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.6053. Min Act: -0.1700
Data Index: 952695 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.6365. Min Act: -0.1700
Data Index: 6686037 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.6365. Min Act: -0.1700
Data Index: 7066586 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9178. Min Range: -5.9178
Max Act: 5.6365. Min Act: -0.1700
Data Index: 2591968 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19