Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 949 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.4806. Min Act: -0.1500
Data Index: 4520717 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.4806. Min Act: -0.1670
Data Index: 5682317 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.4806. Min Act: -0.1662
Data Index: 1578523 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.4806. Min Act: -0.1700
Data Index: 8096216 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.4806. Min Act: -0.1500
Data Index: 8288013 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.4806. Min Act: -0.1700
Data Index: 1510329 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.4181. Min Act: -0.1700
Data Index: 7678225 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.4181. Min Act: -0.1696
Data Index: 1314204 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.4181. Min Act: -0.1700
Data Index: 1255032 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.3556. Min Act: -0.1700
Data Index: 652766 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.3556. Min Act: -0.1696
Data Index: 1915588 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.3556. Min Act: -0.1697
Data Index: 608019 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.3556. Min Act: -0.1700
Data Index: 921280 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.3556. Min Act: -0.1700
Data Index: 16058 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.3556. Min Act: -0.1700
Data Index: 1883938 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.3556. Min Act: -0.1700
Data Index: 133042 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.3556. Min Act: -0.1700
Data Index: 1567234 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.3556. Min Act: -0.1700
Data Index: 867663 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.3556. Min Act: -0.1697
Data Index: 1799733 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.3556. Min Act: -0.1700
Data Index: 1172218 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19