Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1044 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.3263. Min Act: -0.1700
Data Index: 10442 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.3263. Min Act: -0.1700
Data Index: 4632277 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.2951. Min Act: -0.1700
Data Index: 3923541 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.2951. Min Act: -0.1700
Data Index: 6868498 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.2638. Min Act: -0.1700
Data Index: 120684 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.2638. Min Act: -0.1700
Data Index: 2360411 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.2638. Min Act: -0.1700
Data Index: 3010544 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.2326. Min Act: -0.1700
Data Index: 2014953 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.2326. Min Act: -0.1700
Data Index: 6589980 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.2326. Min Act: -0.1699
Data Index: 8040260 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.2638. Min Act: -0.1700
Data Index: 6086154 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.2326. Min Act: -0.1700
Data Index: 7895233 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.2326. Min Act: -0.1700
Data Index: 4049303 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.2013. Min Act: -0.1699
Data Index: 7856278 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.2013. Min Act: -0.1700
Data Index: 5742898 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.2013. Min Act: -0.1700
Data Index: 5418333 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.2013. Min Act: -0.1700
Data Index: 7178367 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.1701. Min Act: -0.1700
Data Index: 6103755 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.1701. Min Act: -0.1700
Data Index: 1498759 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3263. Min Range: -5.3263
Max Act: 5.1701. Min Act: -0.1700
Data Index: 3438835 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19