Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3895 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.9962. Min Act: -0.1700
Data Index: 7502364 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.9337. Min Act: -0.1700
Data Index: 6592080 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.9024. Min Act: -0.1700
Data Index: 26852 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.9024. Min Act: -0.1700
Data Index: 6981606 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.9337. Min Act: -0.1700
Data Index: 6998372 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.8399. Min Act: -0.1700
Data Index: 1355794 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.8399. Min Act: -0.1700
Data Index: 2958316 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.8712. Min Act: -0.1700
Data Index: 168740 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.8399. Min Act: -0.1700
Data Index: 7874282 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.8399. Min Act: -0.1700
Data Index: 3571622 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.7930. Min Act: -0.1700
Data Index: 6087914 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.8086. Min Act: -0.1700
Data Index: 1012792 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.8086. Min Act: -0.1700
Data Index: 3140328 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.7774. Min Act: -0.1700
Data Index: 4473747 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.8086. Min Act: -0.1700
Data Index: 2379789 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.8399. Min Act: -0.1700
Data Index: 4838198 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.8086. Min Act: -0.1700
Data Index: 4211823 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.7930. Min Act: -0.1700
Data Index: 2559508 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.7930. Min Act: -0.1700
Data Index: 7188020 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9962. Min Range: -3.9962
Max Act: 3.7930. Min Act: -0.1700
Data Index: 7846539 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19