Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3090 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0849. Min Range: -4.0849
Max Act: 4.0849. Min Act: -0.1700
Data Index: 5378775 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0849. Min Range: -4.0849
Max Act: 4.0537. Min Act: -0.1700
Data Index: 3730846 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0849. Min Range: -4.0849
Max Act: 4.0224. Min Act: -0.1700
Data Index: 8399250 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0849. Min Range: -4.0849
Max Act: 4.0224. Min Act: -0.1700
Data Index: 4870578 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0849. Min Range: -4.0849
Max Act: 3.9912. Min Act: -0.1700
Data Index: 3503167 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0849. Min Range: -4.0849
Max Act: 3.9599. Min Act: -0.1700
Data Index: 2582975 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0849. Min Range: -4.0849
Max Act: 3.9599. Min Act: -0.1700
Data Index: 576739 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0849. Min Range: -4.0849
Max Act: 3.9599. Min Act: -0.1700
Data Index: 6225168 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0849. Min Range: -4.0849
Max Act: 3.8974. Min Act: -0.1700
Data Index: 5413141 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0849. Min Range: -4.0849
Max Act: 3.9286. Min Act: -0.1700
Data Index: 7011809 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0849. Min Range: -4.0849
Max Act: 3.9286. Min Act: -0.1700
Data Index: 5788288 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0849. Min Range: -4.0849
Max Act: 3.8661. Min Act: -0.1700
Data Index: 2652604 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0849. Min Range: -4.0849
Max Act: 3.8661. Min Act: -0.1700
Data Index: 4826831 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0849. Min Range: -4.0849
Max Act: 3.8661. Min Act: -0.1700
Data Index: 6372909 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0849. Min Range: -4.0849
Max Act: 3.8661. Min Act: -0.1700
Data Index: 1315160 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0849. Min Range: -4.0849
Max Act: 3.8661. Min Act: -0.1700
Data Index: 7837273 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0849. Min Range: -4.0849
Max Act: 3.8661. Min Act: -0.1700
Data Index: 4243216 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0849. Min Range: -4.0849
Max Act: 3.8348. Min Act: -0.1700
Data Index: 7849914 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0849. Min Range: -4.0849
Max Act: 3.8036. Min Act: -0.1700
Data Index: 2667628 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0849. Min Range: -4.0849
Max Act: 3.8192. Min Act: -0.1700
Data Index: 7104903 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19