Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4975 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.1506. Min Act: -0.1700
Data Index: 5590631 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0881. Min Act: -0.1700
Data Index: 8330594 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0881. Min Act: -0.1700
Data Index: 1004129 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0881. Min Act: -0.1700
Data Index: 6429958 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0881. Min Act: -0.1700
Data Index: 1980562 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0881. Min Act: -0.1700
Data Index: 3396556 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0881. Min Act: -0.1700
Data Index: 2633912 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0881. Min Act: -0.1700
Data Index: 1140637 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0256. Min Act: -0.1700
Data Index: 6389264 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0569. Min Act: -0.1698
Data Index: 6224010 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0569. Min Act: -0.1700
Data Index: 5561214 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0569. Min Act: -0.1700
Data Index: 2667098 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0569. Min Act: -0.1700
Data Index: 2425337 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0569. Min Act: -0.1700
Data Index: 4973286 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0569. Min Act: -0.1700
Data Index: 4531022 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0569. Min Act: -0.1700
Data Index: 4286680 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0569. Min Act: -0.1700
Data Index: 4198361 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0569. Min Act: -0.1700
Data Index: 3408915 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0569. Min Act: -0.1700
Data Index: 2177075 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0569. Min Act: -0.1700
Data Index: 1062793 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19