Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2096 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.6255. Min Act: -0.1700
Data Index: 7788471 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.5318. Min Act: -0.1700
Data Index: 6742809 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.5318. Min Act: -0.1700
Data Index: 2783634 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.5005. Min Act: -0.1700
Data Index: 6117742 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.4380. Min Act: -0.1700
Data Index: 6664414 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.4380. Min Act: -0.1700
Data Index: 3814614 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.4380. Min Act: -0.1700
Data Index: 1346641 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.3755. Min Act: -0.1700
Data Index: 8310492 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.4068. Min Act: -0.1700
Data Index: 4997892 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.4068. Min Act: -0.1700
Data Index: 1514672 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.4068. Min Act: -0.1700
Data Index: 5239793 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.4068. Min Act: -0.1700
Data Index: 1773385 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.4068. Min Act: -0.1700
Data Index: 1896160 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.3755. Min Act: -0.1700
Data Index: 5880737 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.3755. Min Act: -0.1700
Data Index: 5868307 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.3755. Min Act: -0.1700
Data Index: 405916 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.3755. Min Act: -0.1700
Data Index: 1933342 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.3755. Min Act: -0.1700
Data Index: 284844 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.3755. Min Act: -0.1700
Data Index: 284835 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6255. Min Range: -4.6255
Max Act: 4.3755. Min Act: -0.1700
Data Index: 4678476 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19