Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2011 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.4243. Min Act: -0.1696
Data Index: 463032 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.4243. Min Act: -0.1700
Data Index: 6368618 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.3931. Min Act: -0.1700
Data Index: 185377 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.2993. Min Act: -0.1700
Data Index: 7999499 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.2681. Min Act: -0.1700
Data Index: 3016166 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.2055. Min Act: -0.1699
Data Index: 2984642 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.2055. Min Act: -0.1700
Data Index: 2493459 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.2055. Min Act: -0.1700
Data Index: 670243 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.2055. Min Act: -0.1700
Data Index: 7633597 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.1118. Min Act: -0.1700
Data Index: 7923194 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.1430. Min Act: -0.1700
Data Index: 4583395 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.1430. Min Act: -0.1700
Data Index: 6030294 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.1118. Min Act: -0.1700
Data Index: 3398065 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.1743. Min Act: -0.1700
Data Index: 281965 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.1430. Min Act: -0.1700
Data Index: 7715818 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.1118. Min Act: -0.1700
Data Index: 5429315 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.1118. Min Act: -0.1700
Data Index: 317354 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.1118. Min Act: -0.1700
Data Index: 5155661 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.1430. Min Act: -0.1700
Data Index: 762306 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4243. Min Range: -4.4243
Max Act: 4.1430. Min Act: -0.1700
Data Index: 3353850 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19