Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5983 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3872. Min Range: -9.3872
Max Act: 9.3872. Min Act: -0.1700
Data Index: 277251 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3872. Min Range: -9.3872
Max Act: 9.2622. Min Act: -0.1700
Data Index: 6787522 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3872. Min Range: -9.3872
Max Act: 9.1997. Min Act: -0.1700
Data Index: 4897751 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3872. Min Range: -9.3872
Max Act: 9.0122. Min Act: -0.1700
Data Index: 1640398 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3872. Min Range: -9.3872
Max Act: 8.8872. Min Act: -0.1700
Data Index: 2199758 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3872. Min Range: -9.3872
Max Act: 8.8872. Min Act: -0.1700
Data Index: 5905645 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3872. Min Range: -9.3872
Max Act: 8.8247. Min Act: -0.1700
Data Index: 1570600 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3872. Min Range: -9.3872
Max Act: 8.8247. Min Act: -0.1700
Data Index: 4296100 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3872. Min Range: -9.3872
Max Act: 8.8247. Min Act: -0.1700
Data Index: 7800529 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3872. Min Range: -9.3872
Max Act: 8.7622. Min Act: -0.1700
Data Index: 3504401 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3872. Min Range: -9.3872
Max Act: 8.7622. Min Act: -0.1700
Data Index: 4812215 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3872. Min Range: -9.3872
Max Act: 8.7622. Min Act: -0.1700
Data Index: 7328094 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3872. Min Range: -9.3872
Max Act: 8.7622. Min Act: -0.1700
Data Index: 515929 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3872. Min Range: -9.3872
Max Act: 8.8247. Min Act: -0.1700
Data Index: 2013944 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3872. Min Range: -9.3872
Max Act: 8.6372. Min Act: -0.1700
Data Index: 677878 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3872. Min Range: -9.3872
Max Act: 8.6997. Min Act: -0.1700
Data Index: 6446163 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3872. Min Range: -9.3872
Max Act: 8.6997. Min Act: -0.1700
Data Index: 7476085 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3872. Min Range: -9.3872
Max Act: 8.6372. Min Act: -0.1700
Data Index: 1332380 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3872. Min Range: -9.3872
Max Act: 8.6372. Min Act: -0.1700
Data Index: 6544577 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3872. Min Range: -9.3872
Max Act: 8.6372. Min Act: -0.1700
Data Index: 2726568 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19