Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 106 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1265. Min Range: -7.1265
Max Act: 7.1265. Min Act: -0.1700
Data Index: 7559409 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1265. Min Range: -7.1265
Max Act: 7.0640. Min Act: -0.1700
Data Index: 2894834 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1265. Min Range: -7.1265
Max Act: 7.0640. Min Act: -0.1700
Data Index: 8380640 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1265. Min Range: -7.1265
Max Act: 7.0640. Min Act: -0.1700
Data Index: 1962228 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1265. Min Range: -7.1265
Max Act: 7.0327. Min Act: -0.1700
Data Index: 1467209 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1265. Min Range: -7.1265
Max Act: 6.9390. Min Act: -0.1700
Data Index: 1416890 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1265. Min Range: -7.1265
Max Act: 6.9077. Min Act: -0.1700
Data Index: 4370545 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1265. Min Range: -7.1265
Max Act: 6.8140. Min Act: -0.1700
Data Index: 6956389 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1265. Min Range: -7.1265
Max Act: 6.7827. Min Act: -0.1700
Data Index: 7974234 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1265. Min Range: -7.1265
Max Act: 6.7202. Min Act: -0.1700
Data Index: 4877775 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1265. Min Range: -7.1265
Max Act: 6.7515. Min Act: -0.1700
Data Index: 1219058 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1265. Min Range: -7.1265
Max Act: 6.7515. Min Act: -0.1700
Data Index: 4992068 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1265. Min Range: -7.1265
Max Act: 6.6577. Min Act: -0.1700
Data Index: 563115 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1265. Min Range: -7.1265
Max Act: 6.7202. Min Act: -0.1700
Data Index: 4465707 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1265. Min Range: -7.1265
Max Act: 6.6577. Min Act: -0.1700
Data Index: 4284006 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1265. Min Range: -7.1265
Max Act: 6.6577. Min Act: -0.1700
Data Index: 8565289 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1265. Min Range: -7.1265
Max Act: 6.6265. Min Act: -0.1700
Data Index: 5170721 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1265. Min Range: -7.1265
Max Act: 6.5952. Min Act: -0.1700
Data Index: 8650716 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1265. Min Range: -7.1265
Max Act: 6.5952. Min Act: -0.1700
Data Index: 4013476 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1265. Min Range: -7.1265
Max Act: 6.5952. Min Act: -0.1700
Data Index: 6096760 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19