Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1978 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.8338. Min Act: -0.1700
Data Index: 1048730 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.7713. Min Act: -0.1700
Data Index: 220509 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.7713. Min Act: -0.1700
Data Index: 5077549 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.6775. Min Act: -0.1700
Data Index: 2683608 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.7088. Min Act: -0.1700
Data Index: 3892459 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.6775. Min Act: -0.1700
Data Index: 2774365 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.6463. Min Act: -0.1700
Data Index: 555156 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.6775. Min Act: -0.1700
Data Index: 8009544 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.6463. Min Act: -0.1700
Data Index: 7167347 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.6463. Min Act: -0.1700
Data Index: 6719795 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.6463. Min Act: -0.1700
Data Index: 4403653 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.6463. Min Act: -0.1700
Data Index: 6013710 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.6775. Min Act: -0.1700
Data Index: 5432893 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.6150. Min Act: -0.1700
Data Index: 3505249 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.6463. Min Act: -0.1700
Data Index: 2196086 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.5838. Min Act: -0.1700
Data Index: 1629738 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.5838. Min Act: -0.1700
Data Index: 1670405 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.6150. Min Act: -0.1700
Data Index: 5577747 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.5838. Min Act: -0.1700
Data Index: 3434937 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8338. Min Range: -4.8338
Max Act: 4.6150. Min Act: -0.1700
Data Index: 448483 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19