Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6015 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.2623. Min Act: -0.1700
Data Index: 7828442 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1685. Min Act: -0.1700
Data Index: 6690071 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1373. Min Act: -0.1700
Data Index: 6853393 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1060. Min Act: -0.1700
Data Index: 1333533 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.0748. Min Act: -0.1700
Data Index: 8692476 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.0748. Min Act: -0.1700
Data Index: 4651757 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.0123. Min Act: -0.1700
Data Index: 2076362 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.0123. Min Act: -0.1700
Data Index: 6880374 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.0123. Min Act: -0.1700
Data Index: 5309098 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2623. Min Range: -5.2623
Max Act: 4.9810. Min Act: -0.1700
Data Index: 1522902 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2623. Min Range: -5.2623
Max Act: 4.9185. Min Act: -0.1700
Data Index: 8735241 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2623. Min Range: -5.2623
Max Act: 4.9498. Min Act: -0.1700
Data Index: 5729857 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2623. Min Range: -5.2623
Max Act: 4.9498. Min Act: -0.1700
Data Index: 8604042 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2623. Min Range: -5.2623
Max Act: 4.9498. Min Act: -0.1700
Data Index: 8625469 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2623. Min Range: -5.2623
Max Act: 4.9185. Min Act: -0.1700
Data Index: 6825910 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2623. Min Range: -5.2623
Max Act: 4.8560. Min Act: -0.1700
Data Index: 5582130 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2623. Min Range: -5.2623
Max Act: 4.8873. Min Act: -0.1700
Data Index: 6657154 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2623. Min Range: -5.2623
Max Act: 4.8873. Min Act: -0.1700
Data Index: 10501 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2623. Min Range: -5.2623
Max Act: 4.8873. Min Act: -0.1700
Data Index: 5618607 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2623. Min Range: -5.2623
Max Act: 4.8873. Min Act: -0.1700
Data Index: 2001160 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19