Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 66 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0420. Min Range: -3.0420
Max Act: 3.0420. Min Act: -0.1700
Data Index: 6274958 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0420. Min Range: -3.0420
Max Act: 3.0104. Min Act: -0.1700
Data Index: 7546763 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0420. Min Range: -3.0420
Max Act: 3.0104. Min Act: -0.1700
Data Index: 7967832 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0420. Min Range: -3.0420
Max Act: 3.0104. Min Act: -0.1700
Data Index: 4296490 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0420. Min Range: -3.0420
Max Act: 3.0104. Min Act: -0.1700
Data Index: 6867866 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9946. Min Act: -0.1700
Data Index: 871414 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9946. Min Act: -0.1700
Data Index: 7622816 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9946. Min Act: -0.1700
Data Index: 4339219 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9788. Min Act: -0.1700
Data Index: 4839761 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9946. Min Act: -0.1700
Data Index: 6774352 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9788. Min Act: -0.1700
Data Index: 1632158 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9788. Min Act: -0.1700
Data Index: 7075839 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9788. Min Act: -0.1700
Data Index: 5467242 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9788. Min Act: -0.1700
Data Index: 5321985 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9629. Min Act: -0.1700
Data Index: 6722334 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9629. Min Act: -0.1700
Data Index: 7149513 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9471. Min Act: -0.1700
Data Index: 6163002 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9471. Min Act: -0.1700
Data Index: 6426442 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9471. Min Act: -0.1700
Data Index: 4298609 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9471. Min Act: -0.1700
Data Index: 3384205 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19