Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1822 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.8432. Min Act: -0.1700
Data Index: 688694 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.5620. Min Act: -0.1700
Data Index: 3874512 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.4370. Min Act: -0.1700
Data Index: 8141710 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.3745. Min Act: -0.1700
Data Index: 5988326 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.3120. Min Act: -0.1700
Data Index: 8101436 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.3120. Min Act: -0.1700
Data Index: 334679 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.2807. Min Act: -0.1700
Data Index: 4815893 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.2807. Min Act: -0.1700
Data Index: 4988040 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.2495. Min Act: -0.1700
Data Index: 5117115 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.2495. Min Act: -0.1700
Data Index: 6204492 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.1870. Min Act: -0.1700
Data Index: 997230 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.2182. Min Act: -0.1700
Data Index: 945152 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.1870. Min Act: -0.1700
Data Index: 8228384 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.1244. Min Act: -0.1700
Data Index: 1089973 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.1557. Min Act: -0.1700
Data Index: 2815198 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.1557. Min Act: -0.1700
Data Index: 4695548 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.1557. Min Act: -0.1700
Data Index: 2621716 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.1870. Min Act: -0.1700
Data Index: 7897308 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.1244. Min Act: -0.1700
Data Index: 1669325 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8432. Min Range: -4.8432
Max Act: 4.1244. Min Act: -0.1700
Data Index: 979338 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19