Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 670 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.7787. Min Act: -0.1700
Data Index: 4322391 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.6224. Min Act: -0.1700
Data Index: 6659010 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.5912. Min Act: -0.1700
Data Index: 5179912 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.6224. Min Act: -0.1699
Data Index: 1222854 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.5912. Min Act: -0.1697
Data Index: 1034753 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.5912. Min Act: -0.1693
Data Index: 3612414 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.5912. Min Act: -0.1700
Data Index: 2292839 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.5912. Min Act: -0.1700
Data Index: 8730141 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.5912. Min Act: -0.1700
Data Index: 5025057 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.5912. Min Act: -0.1699
Data Index: 3486827 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.5912. Min Act: -0.1700
Data Index: 8587594 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.5912. Min Act: -0.1698
Data Index: 450916 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.5912. Min Act: -0.1700
Data Index: 1480212 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.5599. Min Act: -0.1700
Data Index: 7758273 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.5912. Min Act: -0.1700
Data Index: 147657 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.5912. Min Act: -0.1700
Data Index: 4173281 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.5912. Min Act: -0.1700
Data Index: 1795566 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.5912. Min Act: -0.1698
Data Index: 7253991 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.5599. Min Act: -0.1700
Data Index: 4037410 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7787. Min Range: -4.7787
Max Act: 4.5912. Min Act: -0.1700
Data Index: 2885681 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19