Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1645 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0931. Min Range: -7.0931
Max Act: 7.0618. Min Act: -0.1700
Data Index: 6412991 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0931. Min Range: -7.0931
Max Act: 7.0931. Min Act: -0.1700
Data Index: 4885429 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0931. Min Range: -7.0931
Max Act: 6.9993. Min Act: -0.1700
Data Index: 3914830 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0931. Min Range: -7.0931
Max Act: 6.8431. Min Act: -0.1700
Data Index: 5169993 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0931. Min Range: -7.0931
Max Act: 6.8118. Min Act: -0.1700
Data Index: 671237 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0931. Min Range: -7.0931
Max Act: 6.7806. Min Act: -0.1700
Data Index: 8157699 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0931. Min Range: -7.0931
Max Act: 6.7181. Min Act: -0.1700
Data Index: 6631878 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0931. Min Range: -7.0931
Max Act: 6.6868. Min Act: -0.1700
Data Index: 3984658 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0931. Min Range: -7.0931
Max Act: 6.6868. Min Act: -0.1700
Data Index: 7345217 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0931. Min Range: -7.0931
Max Act: 6.6243. Min Act: -0.1700
Data Index: 6710682 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0931. Min Range: -7.0931
Max Act: 6.5931. Min Act: -0.1700
Data Index: 6646892 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0931. Min Range: -7.0931
Max Act: 6.5618. Min Act: -0.1700
Data Index: 1613168 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0931. Min Range: -7.0931
Max Act: 6.5618. Min Act: -0.1700
Data Index: 8451980 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0931. Min Range: -7.0931
Max Act: 6.5931. Min Act: -0.1700
Data Index: 3288305 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0931. Min Range: -7.0931
Max Act: 6.5618. Min Act: -0.1700
Data Index: 7828322 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0931. Min Range: -7.0931
Max Act: 6.4993. Min Act: -0.1700
Data Index: 7198935 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0931. Min Range: -7.0931
Max Act: 6.5306. Min Act: -0.1700
Data Index: 4457982 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0931. Min Range: -7.0931
Max Act: 6.5306. Min Act: -0.1700
Data Index: 340300 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0931. Min Range: -7.0931
Max Act: 6.5306. Min Act: -0.1700
Data Index: 7920567 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0931. Min Range: -7.0931
Max Act: 6.5306. Min Act: -0.1700
Data Index: 4991506 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19