Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3740 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.4699. Min Act: -0.1700
Data Index: 5116427 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.4699. Min Act: -0.1700
Data Index: 8535323 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.3762. Min Act: -0.1700
Data Index: 4010373 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.4074. Min Act: -0.1700
Data Index: 8535322 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.4074. Min Act: -0.1700
Data Index: 4799621 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.4074. Min Act: -0.1700
Data Index: 2898376 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.4074. Min Act: -0.1700
Data Index: 3503909 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.3449. Min Act: -0.1700
Data Index: 8274086 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.3762. Min Act: -0.1700
Data Index: 1681898 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.3449. Min Act: -0.1700
Data Index: 4969684 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.3762. Min Act: -0.1700
Data Index: 2087717 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.3449. Min Act: -0.1700
Data Index: 3011989 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.3136. Min Act: -0.1700
Data Index: 3714897 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.3136. Min Act: -0.1700
Data Index: 414438 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.3136. Min Act: -0.1700
Data Index: 5527640 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.3136. Min Act: -0.1700
Data Index: 8535324 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.2511. Min Act: -0.1700
Data Index: 4765779 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.3136. Min Act: -0.1700
Data Index: 4705094 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.2824. Min Act: -0.1700
Data Index: 5728249 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.2511. Min Act: -0.1700
Data Index: 663822 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19