Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1154 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.9711. Min Act: -0.1700
Data Index: 1231324 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.9711. Min Act: -0.1700
Data Index: 1312082 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.9553. Min Act: -0.1699
Data Index: 1667594 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.9553. Min Act: -0.1699
Data Index: 117203 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.9553. Min Act: -0.1700
Data Index: 2148333 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.9236. Min Act: -0.1696
Data Index: 5382780 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.8919. Min Act: -0.1700
Data Index: 7494711 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.8760. Min Act: -0.1700
Data Index: 5101483 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.8443. Min Act: -0.1694
Data Index: 1219644 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.8284. Min Act: -0.1696
Data Index: 3465939 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.8284. Min Act: -0.1700
Data Index: 4320964 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.8125. Min Act: -0.1698
Data Index: 7037435 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.7965. Min Act: -0.1699
Data Index: 3819535 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.7965. Min Act: -0.1691
Data Index: 4444866 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.7806. Min Act: -0.1697
Data Index: 236461 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.7806. Min Act: -0.1700
Data Index: 6339789 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.8125. Min Act: -0.1700
Data Index: 1951790 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.7806. Min Act: -0.1694
Data Index: 6201548 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.7965. Min Act: -0.1697
Data Index: 5866101 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9711. Min Range: -2.9711
Max Act: 2.7965. Min Act: -0.1698
Data Index: 534106 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19