Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2918 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.9276. Min Act: -0.1700
Data Index: 5116518 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.8651. Min Act: -0.1700
Data Index: 2293663 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.7714. Min Act: -0.1700
Data Index: 4794863 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.5526. Min Act: -0.1700
Data Index: 6129562 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.4276. Min Act: -0.1700
Data Index: 3036356 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.3964. Min Act: -0.1700
Data Index: 3957753 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.4276. Min Act: -0.1700
Data Index: 1599752 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.3651. Min Act: -0.1700
Data Index: 1315381 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.3651. Min Act: -0.1700
Data Index: 7572187 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.3651. Min Act: -0.1700
Data Index: 5955385 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.3339. Min Act: -0.1700
Data Index: 7465201 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.3026. Min Act: -0.1700
Data Index: 1557951 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.3026. Min Act: -0.1700
Data Index: 7544603 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.3026. Min Act: -0.1700
Data Index: 4513319 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.3026. Min Act: -0.1700
Data Index: 1726234 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.3026. Min Act: -0.1700
Data Index: 5120830 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.2714. Min Act: -0.1700
Data Index: 3639513 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.2714. Min Act: -0.1700
Data Index: 665418 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.2401. Min Act: -0.1700
Data Index: 6609866 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.2401. Min Act: -0.1700
Data Index: 3049455 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19