Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3249 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0881. Min Range: -8.0881
Max Act: 8.0256. Min Act: -0.1700
Data Index: 7097458 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0881. Min Range: -8.0881
Max Act: 8.0881. Min Act: -0.1700
Data Index: 1213952 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0881. Min Range: -8.0881
Max Act: 7.9318. Min Act: -0.1700
Data Index: 7935316 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0881. Min Range: -8.0881
Max Act: 7.8381. Min Act: -0.1700
Data Index: 1428061 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0881. Min Range: -8.0881
Max Act: 7.8381. Min Act: -0.1700
Data Index: 2447855 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0881. Min Range: -8.0881
Max Act: 7.8693. Min Act: -0.1700
Data Index: 1331357 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0881. Min Range: -8.0881
Max Act: 7.7756. Min Act: -0.1700
Data Index: 4447271 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0881. Min Range: -8.0881
Max Act: 7.6818. Min Act: -0.1700
Data Index: 6312329 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0881. Min Range: -8.0881
Max Act: 7.7443. Min Act: -0.1700
Data Index: 6975398 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0881. Min Range: -8.0881
Max Act: 7.7131. Min Act: -0.1700
Data Index: 2890471 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0881. Min Range: -8.0881
Max Act: 7.6506. Min Act: -0.1700
Data Index: 3136492 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0881. Min Range: -8.0881
Max Act: 7.6506. Min Act: -0.1700
Data Index: 2590288 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0881. Min Range: -8.0881
Max Act: 7.6193. Min Act: -0.1700
Data Index: 2814890 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0881. Min Range: -8.0881
Max Act: 7.6506. Min Act: -0.1700
Data Index: 6740055 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0881. Min Range: -8.0881
Max Act: 7.6506. Min Act: -0.1700
Data Index: 8356996 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0881. Min Range: -8.0881
Max Act: 7.6193. Min Act: -0.1700
Data Index: 4108059 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0881. Min Range: -8.0881
Max Act: 7.5881. Min Act: -0.1700
Data Index: 5038246 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0881. Min Range: -8.0881
Max Act: 7.5881. Min Act: -0.1700
Data Index: 74886 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0881. Min Range: -8.0881
Max Act: 7.5256. Min Act: -0.1700
Data Index: 8366587 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0881. Min Range: -8.0881
Max Act: 7.5256. Min Act: -0.1700
Data Index: 6127863 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19