Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2245 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.8024. Min Act: -0.1700
Data Index: 7537819 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.7399. Min Act: -0.1700
Data Index: 388112 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.6462. Min Act: -0.1700
Data Index: 854131 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.6149. Min Act: -0.1700
Data Index: 1532517 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.5837. Min Act: -0.1700
Data Index: 4258542 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.5524. Min Act: -0.1700
Data Index: 4240049 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.5524. Min Act: -0.1700
Data Index: 1659344 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.5524. Min Act: -0.1700
Data Index: 4755138 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.5524. Min Act: -0.1700
Data Index: 1227013 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.5212. Min Act: -0.1700
Data Index: 1120883 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.4899. Min Act: -0.1700
Data Index: 3885700 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.4899. Min Act: -0.1700
Data Index: 2801641 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.4899. Min Act: -0.1700
Data Index: 8522378 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.5212. Min Act: -0.1700
Data Index: 4680889 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.4899. Min Act: -0.1700
Data Index: 7474373 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.4899. Min Act: -0.1700
Data Index: 8221554 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.4899. Min Act: -0.1700
Data Index: 1456803 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.4587. Min Act: -0.1700
Data Index: 7168842 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.4587. Min Act: -0.1700
Data Index: 4821095 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8024. Min Range: -4.8024
Max Act: 4.4587. Min Act: -0.1700
Data Index: 5089651 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19