Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3575 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.8240. Min Act: -0.1700
Data Index: 5218579 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.6990. Min Act: -0.1700
Data Index: 8587970 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.6677. Min Act: -0.1700
Data Index: 5968055 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.6677. Min Act: -0.1700
Data Index: 2404501 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.6365. Min Act: -0.1700
Data Index: 5199247 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.6365. Min Act: -0.1700
Data Index: 8703118 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.6365. Min Act: -0.1700
Data Index: 6820951 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.6365. Min Act: -0.1700
Data Index: 1391740 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.6365. Min Act: -0.1700
Data Index: 8832503 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.6052. Min Act: -0.1700
Data Index: 3320680 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.6365. Min Act: -0.1700
Data Index: 2175912 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5740. Min Act: -0.1700
Data Index: 1051334 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5740. Min Act: -0.1700
Data Index: 1051335 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5427. Min Act: -0.1700
Data Index: 2184800 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5427. Min Act: -0.1700
Data Index: 7325942 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5427. Min Act: -0.1700
Data Index: 1056294 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5740. Min Act: -0.1700
Data Index: 781847 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5427. Min Act: -0.1699
Data Index: 1140052 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5115. Min Act: -0.1700
Data Index: 2846577 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5115. Min Act: -0.1700
Data Index: 671196 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19