Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2807 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0787. Min Range: -4.0787
Max Act: 4.0787. Min Act: -0.1700
Data Index: 3937423 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0787. Min Range: -4.0787
Max Act: 4.0787. Min Act: -0.1700
Data Index: 7411995 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0787. Min Range: -4.0787
Max Act: 4.0474. Min Act: -0.1700
Data Index: 7686507 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0787. Min Range: -4.0787
Max Act: 4.0162. Min Act: -0.1700
Data Index: 3759672 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0787. Min Range: -4.0787
Max Act: 4.0162. Min Act: -0.1700
Data Index: 7411994 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0787. Min Range: -4.0787
Max Act: 3.9849. Min Act: -0.1700
Data Index: 6689304 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0787. Min Range: -4.0787
Max Act: 3.9536. Min Act: -0.1700
Data Index: 8192070 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0787. Min Range: -4.0787
Max Act: 3.8911. Min Act: -0.1700
Data Index: 4190558 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0787. Min Range: -4.0787
Max Act: 3.9224. Min Act: -0.1700
Data Index: 1480453 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0787. Min Range: -4.0787
Max Act: 3.8599. Min Act: -0.1700
Data Index: 5258400 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0787. Min Range: -4.0787
Max Act: 3.8599. Min Act: -0.1700
Data Index: 1676288 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0787. Min Range: -4.0787
Max Act: 3.8911. Min Act: -0.1700
Data Index: 6215478 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0787. Min Range: -4.0787
Max Act: 3.8911. Min Act: -0.1700
Data Index: 5160831 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0787. Min Range: -4.0787
Max Act: 3.8599. Min Act: -0.1700
Data Index: 3024178 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0787. Min Range: -4.0787
Max Act: 3.9224. Min Act: -0.1700
Data Index: 3949481 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0787. Min Range: -4.0787
Max Act: 3.8599. Min Act: -0.1700
Data Index: 7058906 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0787. Min Range: -4.0787
Max Act: 3.8286. Min Act: -0.1700
Data Index: 6796010 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0787. Min Range: -4.0787
Max Act: 3.8599. Min Act: -0.1700
Data Index: 4606834 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0787. Min Range: -4.0787
Max Act: 3.8286. Min Act: -0.1700
Data Index: 5984691 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0787. Min Range: -4.0787
Max Act: 3.8286. Min Act: -0.1700
Data Index: 1129932 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19