Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2161 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2086. Min Range: -7.2086
Max Act: 7.1773. Min Act: -0.1700
Data Index: 6499343 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2086. Min Range: -7.2086
Max Act: 7.2086. Min Act: -0.1700
Data Index: 5020065 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2086. Min Range: -7.2086
Max Act: 7.1773. Min Act: -0.1700
Data Index: 1463647 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2086. Min Range: -7.2086
Max Act: 7.1773. Min Act: -0.1700
Data Index: 6546829 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2086. Min Range: -7.2086
Max Act: 7.1148. Min Act: -0.1700
Data Index: 7645263 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2086. Min Range: -7.2086
Max Act: 7.0836. Min Act: -0.1700
Data Index: 1327012 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2086. Min Range: -7.2086
Max Act: 7.0523. Min Act: -0.1700
Data Index: 6478900 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2086. Min Range: -7.2086
Max Act: 7.0523. Min Act: -0.1700
Data Index: 1271977 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2086. Min Range: -7.2086
Max Act: 7.0523. Min Act: -0.1700
Data Index: 3297284 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2086. Min Range: -7.2086
Max Act: 7.0211. Min Act: -0.1700
Data Index: 4638725 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2086. Min Range: -7.2086
Max Act: 7.0211. Min Act: -0.1700
Data Index: 6162085 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2086. Min Range: -7.2086
Max Act: 6.9898. Min Act: -0.1700
Data Index: 727054 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2086. Min Range: -7.2086
Max Act: 6.9898. Min Act: -0.1700
Data Index: 7470454 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2086. Min Range: -7.2086
Max Act: 6.9898. Min Act: -0.1700
Data Index: 1654091 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2086. Min Range: -7.2086
Max Act: 6.9898. Min Act: -0.1700
Data Index: 4273208 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2086. Min Range: -7.2086
Max Act: 6.9586. Min Act: -0.1700
Data Index: 6435719 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2086. Min Range: -7.2086
Max Act: 6.8961. Min Act: -0.1700
Data Index: 6234954 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2086. Min Range: -7.2086
Max Act: 6.8961. Min Act: -0.1700
Data Index: 1378028 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2086. Min Range: -7.2086
Max Act: 6.8961. Min Act: -0.1700
Data Index: 6330494 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2086. Min Range: -7.2086
Max Act: 6.8961. Min Act: -0.1700
Data Index: 7492330 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19