Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3046 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.4221. Min Act: -0.1699
Data Index: 7928588 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.2105. Min Act: -0.1700
Data Index: 3302018 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.2105. Min Act: -0.1700
Data Index: 6649154 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.2281. Min Act: -0.1681
Data Index: 7869665 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.2105. Min Act: -0.1698
Data Index: 5901119 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.1929. Min Act: -0.1700
Data Index: 2156274 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.1577. Min Act: -0.1699
Data Index: 8647681 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.1577. Min Act: -0.1700
Data Index: 3492377 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.1577. Min Act: -0.1700
Data Index: 4754263 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.1577. Min Act: -0.1700
Data Index: 2488581 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.1226. Min Act: -0.1700
Data Index: 7857257 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.1401. Min Act: -0.1700
Data Index: 5973828 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.1401. Min Act: -0.1700
Data Index: 7822908 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.1051. Min Act: -0.1700
Data Index: 7288088 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.1051. Min Act: -0.1698
Data Index: 2888355 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.1051. Min Act: -0.1700
Data Index: 2578342 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.1051. Min Act: -0.1700
Data Index: 5901118 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.1051. Min Act: -0.1700
Data Index: 6523952 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.1051. Min Act: -0.1700
Data Index: 2365465 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4221. Min Range: -1.4221
Max Act: 1.1051. Min Act: -0.1700
Data Index: 4159705 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19