Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2488. Min Range: -4.2488
Max Act: 4.2488. Min Act: -0.1700
Data Index: 5896325 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2488. Min Range: -4.2488
Max Act: 4.1863. Min Act: -0.1700
Data Index: 7564396 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2488. Min Range: -4.2488
Max Act: 4.0300. Min Act: -0.1700
Data Index: 8403194 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2488. Min Range: -4.2488
Max Act: 4.0613. Min Act: -0.1700
Data Index: 6782704 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2488. Min Range: -4.2488
Max Act: 3.9988. Min Act: -0.1700
Data Index: 97825 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2488. Min Range: -4.2488
Max Act: 4.0613. Min Act: -0.1700
Data Index: 6860929 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2488. Min Range: -4.2488
Max Act: 4.0613. Min Act: -0.1700
Data Index: 5515867 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2488. Min Range: -4.2488
Max Act: 4.0925. Min Act: -0.1700
Data Index: 2412458 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2488. Min Range: -4.2488
Max Act: 4.0300. Min Act: -0.1700
Data Index: 7341852 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2488. Min Range: -4.2488
Max Act: 3.9675. Min Act: -0.1700
Data Index: 8282368 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2488. Min Range: -4.2488
Max Act: 3.9988. Min Act: -0.1700
Data Index: 8354580 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2488. Min Range: -4.2488
Max Act: 3.9675. Min Act: -0.1700
Data Index: 1189453 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2488. Min Range: -4.2488
Max Act: 3.9675. Min Act: -0.1700
Data Index: 2458430 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2488. Min Range: -4.2488
Max Act: 3.9675. Min Act: -0.1700
Data Index: 6493598 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2488. Min Range: -4.2488
Max Act: 3.9675. Min Act: -0.1700
Data Index: 7341838 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2488. Min Range: -4.2488
Max Act: 3.9675. Min Act: -0.1700
Data Index: 4845413 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2488. Min Range: -4.2488
Max Act: 3.9675. Min Act: -0.1700
Data Index: 2060169 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2488. Min Range: -4.2488
Max Act: 3.9362. Min Act: -0.1700
Data Index: 3576427 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2488. Min Range: -4.2488
Max Act: 3.9050. Min Act: -0.1700
Data Index: 1700896 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2488. Min Range: -4.2488
Max Act: 3.9362. Min Act: -0.1700
Data Index: 7508441 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19