Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 287 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3489. Min Range: -9.3489
Max Act: 9.3489. Min Act: -0.1700
Data Index: 7658935 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3489. Min Range: -9.3489
Max Act: 9.0364. Min Act: -0.1700
Data Index: 1978610 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3489. Min Range: -9.3489
Max Act: 8.3489. Min Act: -0.1700
Data Index: 6788004 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3489. Min Range: -9.3489
Max Act: 8.2864. Min Act: -0.1700
Data Index: 7437008 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3489. Min Range: -9.3489
Max Act: 8.0989. Min Act: -0.1700
Data Index: 6752717 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3489. Min Range: -9.3489
Max Act: 8.0989. Min Act: -0.1700
Data Index: 884814 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3489. Min Range: -9.3489
Max Act: 8.0364. Min Act: -0.1700
Data Index: 1755843 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3489. Min Range: -9.3489
Max Act: 8.0364. Min Act: -0.1700
Data Index: 5680150 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3489. Min Range: -9.3489
Max Act: 8.0364. Min Act: -0.1700
Data Index: 3394286 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3489. Min Range: -9.3489
Max Act: 7.9739. Min Act: -0.1700
Data Index: 3419906 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3489. Min Range: -9.3489
Max Act: 7.9739. Min Act: -0.1700
Data Index: 1842970 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3489. Min Range: -9.3489
Max Act: 7.9114. Min Act: -0.1700
Data Index: 1188570 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3489. Min Range: -9.3489
Max Act: 7.9739. Min Act: -0.1700
Data Index: 5866940 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3489. Min Range: -9.3489
Max Act: 7.9114. Min Act: -0.1700
Data Index: 675072 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3489. Min Range: -9.3489
Max Act: 7.9114. Min Act: -0.1700
Data Index: 506501 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3489. Min Range: -9.3489
Max Act: 7.9114. Min Act: -0.1700
Data Index: 4815704 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3489. Min Range: -9.3489
Max Act: 7.9114. Min Act: -0.1700
Data Index: 4406421 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3489. Min Range: -9.3489
Max Act: 7.8489. Min Act: -0.1700
Data Index: 6889922 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3489. Min Range: -9.3489
Max Act: 7.8489. Min Act: -0.1700
Data Index: 6468823 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3489. Min Range: -9.3489
Max Act: 7.8489. Min Act: -0.1700
Data Index: 1733678 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19