Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 49 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0501. Min Range: -5.0501
Max Act: 5.0501. Min Act: -0.1700
Data Index: 677885 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0501. Min Range: -5.0501
Max Act: 5.0189. Min Act: -0.1700
Data Index: 8101360 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0501. Min Range: -5.0501
Max Act: 5.0189. Min Act: -0.1700
Data Index: 2087905 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0501. Min Range: -5.0501
Max Act: 4.9876. Min Act: -0.1700
Data Index: 2351029 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0501. Min Range: -5.0501
Max Act: 4.9876. Min Act: -0.1700
Data Index: 1171281 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0501. Min Range: -5.0501
Max Act: 4.9251. Min Act: -0.1700
Data Index: 4773117 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0501. Min Range: -5.0501
Max Act: 4.9564. Min Act: -0.1700
Data Index: 3515988 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0501. Min Range: -5.0501
Max Act: 4.9251. Min Act: -0.1700
Data Index: 2070740 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0501. Min Range: -5.0501
Max Act: 4.8939. Min Act: -0.1700
Data Index: 4837181 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0501. Min Range: -5.0501
Max Act: 4.8939. Min Act: -0.1700
Data Index: 6779145 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0501. Min Range: -5.0501
Max Act: 4.8939. Min Act: -0.1700
Data Index: 6533268 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0501. Min Range: -5.0501
Max Act: 4.8626. Min Act: -0.1700
Data Index: 658298 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0501. Min Range: -5.0501
Max Act: 4.8626. Min Act: -0.1700
Data Index: 5304433 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0501. Min Range: -5.0501
Max Act: 4.8314. Min Act: -0.1700
Data Index: 1060433 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0501. Min Range: -5.0501
Max Act: 4.8626. Min Act: -0.1700
Data Index: 6253113 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0501. Min Range: -5.0501
Max Act: 4.8314. Min Act: -0.1700
Data Index: 5450595 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0501. Min Range: -5.0501
Max Act: 4.8314. Min Act: -0.1700
Data Index: 579721 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0501. Min Range: -5.0501
Max Act: 4.8314. Min Act: -0.1700
Data Index: 6750305 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0501. Min Range: -5.0501
Max Act: 4.8314. Min Act: -0.1700
Data Index: 5893391 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0501. Min Range: -5.0501
Max Act: 4.8314. Min Act: -0.1700
Data Index: 6360341 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19