Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1465 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.5184. Min Act: -0.1700
Data Index: 3569097 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.4860. Min Act: -0.1700
Data Index: 4881771 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.4210. Min Act: -0.1700
Data Index: 1864467 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.4047. Min Act: -0.1700
Data Index: 7732443 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.3392. Min Act: -0.1700
Data Index: 1122457 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.2735. Min Act: -0.1700
Data Index: 6949049 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.2735. Min Act: -0.1700
Data Index: 8745666 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.2570. Min Act: -0.1700
Data Index: 3026989 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.2570. Min Act: -0.1700
Data Index: 5910869 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.2404. Min Act: -0.1700
Data Index: 3792520 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.2073. Min Act: -0.1700
Data Index: 5470923 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.2239. Min Act: -0.1700
Data Index: 6613496 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.1907. Min Act: -0.1700
Data Index: 4503564 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.1907. Min Act: -0.1700
Data Index: 2860720 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.2073. Min Act: -0.1700
Data Index: 1833046 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.2239. Min Act: -0.1700
Data Index: 7547260 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.2239. Min Act: -0.1700
Data Index: 2890807 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.2073. Min Act: -0.1700
Data Index: 7125263 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.2073. Min Act: -0.1700
Data Index: 2231306 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5184. Min Range: -2.5184
Max Act: 2.1907. Min Act: -0.1700
Data Index: 6785846 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19