Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1438 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0423. Min Range: -7.0423
Max Act: 7.0423. Min Act: -0.1700
Data Index: 6971944 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.9798. Min Act: -0.1700
Data Index: 3325322 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.9798. Min Act: -0.1700
Data Index: 8007488 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.9173. Min Act: -0.1700
Data Index: 1519369 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.8861. Min Act: -0.1700
Data Index: 2085893 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.8236. Min Act: -0.1700
Data Index: 5673250 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.7611. Min Act: -0.1700
Data Index: 8358844 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.7923. Min Act: -0.1700
Data Index: 6772316 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.7923. Min Act: -0.1700
Data Index: 1537275 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.7611. Min Act: -0.1700
Data Index: 7789239 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.7611. Min Act: -0.1700
Data Index: 1521832 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.7923. Min Act: -0.1700
Data Index: 1823920 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.7923. Min Act: -0.1700
Data Index: 6731510 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.7298. Min Act: -0.1698
Data Index: 5593927 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.7298. Min Act: -0.1700
Data Index: 288177 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.7298. Min Act: -0.1700
Data Index: 3809029 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.7298. Min Act: -0.1700
Data Index: 6414372 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.6986. Min Act: -0.1700
Data Index: 6096929 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.7298. Min Act: -0.1700
Data Index: 3686964 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0423. Min Range: -7.0423
Max Act: 6.6673. Min Act: -0.1700
Data Index: 5841144 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19