Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 962 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.8826. Min Act: -0.1700
Data Index: 4979954 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.5701. Min Act: -0.1700
Data Index: 3284704 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.4763. Min Act: -0.1700
Data Index: 4647747 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.2888. Min Act: -0.1700
Data Index: 320964 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.2575. Min Act: -0.1700
Data Index: 1362951 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.2575. Min Act: -0.1700
Data Index: 5456130 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.2575. Min Act: -0.1700
Data Index: 427592 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.1950. Min Act: -0.1700
Data Index: 1679453 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.2263. Min Act: -0.1700
Data Index: 8696371 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.1638. Min Act: -0.1700
Data Index: 2983356 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.1638. Min Act: -0.1700
Data Index: 2460628 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.1638. Min Act: -0.1700
Data Index: 4718031 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.1638. Min Act: -0.1700
Data Index: 870793 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.1638. Min Act: -0.1700
Data Index: 1035493 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.1638. Min Act: -0.1700
Data Index: 6590272 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.1638. Min Act: -0.1700
Data Index: 1898602 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.1638. Min Act: -0.1700
Data Index: 2272610 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.1638. Min Act: -0.1700
Data Index: 5097577 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.1638. Min Act: -0.1700
Data Index: 1056353 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8826. Min Range: -4.8826
Max Act: 4.1325. Min Act: -0.1700
Data Index: 4864856 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19