Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5286 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0705. Min Range: -7.0705
Max Act: 7.0705. Min Act: -0.1700
Data Index: 6225799 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0705. Min Range: -7.0705
Max Act: 7.0393. Min Act: -0.1700
Data Index: 7161472 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0705. Min Range: -7.0705
Max Act: 7.0393. Min Act: -0.1700
Data Index: 7850976 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0705. Min Range: -7.0705
Max Act: 6.9143. Min Act: -0.1700
Data Index: 238488 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0705. Min Range: -7.0705
Max Act: 6.9143. Min Act: -0.1700
Data Index: 1199243 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0705. Min Range: -7.0705
Max Act: 6.8518. Min Act: -0.1700
Data Index: 5830409 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0705. Min Range: -7.0705
Max Act: 6.8830. Min Act: -0.1700
Data Index: 7901932 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0705. Min Range: -7.0705
Max Act: 6.8518. Min Act: -0.1700
Data Index: 8555209 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0705. Min Range: -7.0705
Max Act: 6.8830. Min Act: -0.1700
Data Index: 2463443 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0705. Min Range: -7.0705
Max Act: 6.8518. Min Act: -0.1700
Data Index: 1461203 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0705. Min Range: -7.0705
Max Act: 6.8205. Min Act: -0.1700
Data Index: 5038115 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0705. Min Range: -7.0705
Max Act: 6.7893. Min Act: -0.1700
Data Index: 1126786 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0705. Min Range: -7.0705
Max Act: 6.8205. Min Act: -0.1700
Data Index: 7208954 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0705. Min Range: -7.0705
Max Act: 6.8205. Min Act: -0.1700
Data Index: 4216959 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0705. Min Range: -7.0705
Max Act: 6.8205. Min Act: -0.1700
Data Index: 1772414 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0705. Min Range: -7.0705
Max Act: 6.7893. Min Act: -0.1700
Data Index: 6686837 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0705. Min Range: -7.0705
Max Act: 6.7580. Min Act: -0.1700
Data Index: 1377516 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0705. Min Range: -7.0705
Max Act: 6.7893. Min Act: -0.1700
Data Index: 4296435 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0705. Min Range: -7.0705
Max Act: 6.7580. Min Act: -0.1700
Data Index: 7419835 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0705. Min Range: -7.0705
Max Act: 6.7268. Min Act: -0.1700
Data Index: 6954370 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19