Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2861 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1749. Min Range: -11.1749
Max Act: 11.1749. Min Act: -0.1700
Data Index: 5045019 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.7374. Min Act: -0.1700
Data Index: 3674152 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.6124. Min Act: -0.1700
Data Index: 6361299 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.6124. Min Act: -0.1700
Data Index: 1347346 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.5499. Min Act: -0.1700
Data Index: 3525737 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.5499. Min Act: -0.1700
Data Index: 6634155 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.4874. Min Act: -0.1700
Data Index: 7547172 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.4874. Min Act: -0.1700
Data Index: 3502420 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.4874. Min Act: -0.1700
Data Index: 7073723 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.4249. Min Act: -0.1700
Data Index: 2406623 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.4249. Min Act: -0.1700
Data Index: 4206545 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.3624. Min Act: -0.1700
Data Index: 7270706 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.3624. Min Act: -0.1700
Data Index: 6913266 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.2999. Min Act: -0.1700
Data Index: 5175045 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.2999. Min Act: -0.1700
Data Index: 2190473 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.2374. Min Act: -0.1700
Data Index: 8532427 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.2374. Min Act: -0.1700
Data Index: 4733437 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.1749. Min Act: -0.1700
Data Index: 4693140 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.1749. Min Act: -0.1700
Data Index: 6558687 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1749. Min Range: -11.1749
Max Act: 10.1749. Min Act: -0.1700
Data Index: 2950032 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19