Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3978 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.4454. Min Act: -0.1700
Data Index: 1881717 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.4454. Min Act: -0.1700
Data Index: 4895945 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.4454. Min Act: -0.1700
Data Index: 601470 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.3984. Min Act: -0.1700
Data Index: 8619957 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.3984. Min Act: -0.1700
Data Index: 3995506 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.3670. Min Act: -0.1700
Data Index: 1516429 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.3670. Min Act: -0.1700
Data Index: 1901029 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.3670. Min Act: -0.1700
Data Index: 7801727 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.3357. Min Act: -0.1700
Data Index: 3353722 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.3200. Min Act: -0.1700
Data Index: 5907954 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.3200. Min Act: -0.1700
Data Index: 3288993 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.3357. Min Act: -0.1700
Data Index: 7635023 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.3200. Min Act: -0.1700
Data Index: 6347852 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.3513. Min Act: -0.1700
Data Index: 7677804 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.3357. Min Act: -0.1700
Data Index: 3020773 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.3357. Min Act: -0.1700
Data Index: 2842302 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.3357. Min Act: -0.1700
Data Index: 5594565 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.3357. Min Act: -0.1700
Data Index: 5887123 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.3357. Min Act: -0.1700
Data Index: 2472694 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4454. Min Range: -3.4454
Max Act: 3.3200. Min Act: -0.1700
Data Index: 648001 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19