Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2452 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0447. Min Range: -4.0447
Max Act: 4.0447. Min Act: -0.1700
Data Index: 3753972 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0447. Min Range: -4.0447
Max Act: 4.0134. Min Act: -0.1700
Data Index: 460295 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0447. Min Range: -4.0447
Max Act: 4.0134. Min Act: -0.1700
Data Index: 3753976 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.9822. Min Act: -0.1700
Data Index: 7730755 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.9822. Min Act: -0.1700
Data Index: 6916060 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.9822. Min Act: -0.1700
Data Index: 2018315 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.9822. Min Act: -0.1700
Data Index: 3753970 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.9509. Min Act: -0.1700
Data Index: 2329060 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.9509. Min Act: -0.1700
Data Index: 3145535 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.9197. Min Act: -0.1700
Data Index: 3867216 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.9509. Min Act: -0.1700
Data Index: 5360905 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.9197. Min Act: -0.1700
Data Index: 5440135 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.8884. Min Act: -0.1700
Data Index: 156150 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.9197. Min Act: -0.1700
Data Index: 4840953 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.9509. Min Act: -0.1700
Data Index: 4553969 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.9197. Min Act: -0.1700
Data Index: 7334987 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.8884. Min Act: -0.1700
Data Index: 6504208 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.8884. Min Act: -0.1700
Data Index: 4275731 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.8884. Min Act: -0.1700
Data Index: 1018261 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.8571. Min Act: -0.1700
Data Index: 4264261 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19