Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4995 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.3116. Min Act: -0.1700
Data Index: 7410928 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2587. Min Act: -0.1700
Data Index: 981623 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2587. Min Act: -0.1700
Data Index: 5617726 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2411. Min Act: -0.1700
Data Index: 7610290 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2411. Min Act: -0.1700
Data Index: 6249099 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2411. Min Act: -0.1700
Data Index: 4332810 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2411. Min Act: -0.1700
Data Index: 847625 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2411. Min Act: -0.1700
Data Index: 474148 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2235. Min Act: -0.1700
Data Index: 2225128 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2411. Min Act: -0.1700
Data Index: 2753877 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2411. Min Act: -0.1700
Data Index: 6647354 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2235. Min Act: -0.1700
Data Index: 8696827 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2235. Min Act: -0.1700
Data Index: 2095041 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2235. Min Act: -0.1700
Data Index: 4132015 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2235. Min Act: -0.1700
Data Index: 8097259 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2235. Min Act: -0.1700
Data Index: 4261944 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2235. Min Act: -0.1700
Data Index: 2609739 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2235. Min Act: -0.1700
Data Index: 6311942 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2059. Min Act: -0.1700
Data Index: 7295261 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3116. Min Range: -1.3116
Max Act: 1.2059. Min Act: -0.1700
Data Index: 6199926 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19