Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2085 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.8123. Min Act: -0.1700
Data Index: 2410403 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.8123. Min Act: -0.1700
Data Index: 3184399 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.8123. Min Act: -0.1700
Data Index: 6088982 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.8123. Min Act: -0.1700
Data Index: 284032 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.7810. Min Act: -0.1700
Data Index: 2070632 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.7498. Min Act: -0.1700
Data Index: 7692729 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.7498. Min Act: -0.1700
Data Index: 271603 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.7498. Min Act: -0.1700
Data Index: 6386735 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.7498. Min Act: -0.1695
Data Index: 4302205 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.6873. Min Act: -0.1700
Data Index: 4899255 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.6873. Min Act: -0.1700
Data Index: 4840778 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.6873. Min Act: -0.1700
Data Index: 637852 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.6873. Min Act: -0.1700
Data Index: 2124702 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.6873. Min Act: -0.1700
Data Index: 8238825 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.6873. Min Act: -0.1700
Data Index: 85283 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.6873. Min Act: -0.1686
Data Index: 225757 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.6248. Min Act: -0.1699
Data Index: 1019551 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.6248. Min Act: -0.1700
Data Index: 748986 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.6248. Min Act: -0.1699
Data Index: 263490 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8123. Min Range: -4.8123
Max Act: 4.6560. Min Act: -0.1700
Data Index: 4026574 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19