Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4343 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0695. Min Range: -5.0695
Max Act: 5.0695. Min Act: -0.1700
Data Index: 7014289 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0695. Min Range: -5.0695
Max Act: 5.0070. Min Act: -0.1700
Data Index: 183498 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0695. Min Range: -5.0695
Max Act: 5.0070. Min Act: -0.1700
Data Index: 1435154 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0695. Min Range: -5.0695
Max Act: 4.9445. Min Act: -0.1700
Data Index: 6177705 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0695. Min Range: -5.0695
Max Act: 4.8820. Min Act: -0.1700
Data Index: 4566431 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0695. Min Range: -5.0695
Max Act: 4.8820. Min Act: -0.1700
Data Index: 1449437 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0695. Min Range: -5.0695
Max Act: 4.8507. Min Act: -0.1700
Data Index: 4465794 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0695. Min Range: -5.0695
Max Act: 4.8195. Min Act: -0.1700
Data Index: 6156940 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0695. Min Range: -5.0695
Max Act: 4.7882. Min Act: -0.1700
Data Index: 2199386 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0695. Min Range: -5.0695
Max Act: 4.7882. Min Act: -0.1700
Data Index: 2336498 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0695. Min Range: -5.0695
Max Act: 4.8195. Min Act: -0.1700
Data Index: 2135369 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0695. Min Range: -5.0695
Max Act: 4.7882. Min Act: -0.1700
Data Index: 401498 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0695. Min Range: -5.0695
Max Act: 4.7570. Min Act: -0.1700
Data Index: 7953010 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0695. Min Range: -5.0695
Max Act: 4.7257. Min Act: -0.1700
Data Index: 63094 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0695. Min Range: -5.0695
Max Act: 4.7257. Min Act: -0.1700
Data Index: 4665581 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0695. Min Range: -5.0695
Max Act: 4.7257. Min Act: -0.1700
Data Index: 1486416 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0695. Min Range: -5.0695
Max Act: 4.7257. Min Act: -0.1700
Data Index: 5086924 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0695. Min Range: -5.0695
Max Act: 4.7257. Min Act: -0.1700
Data Index: 13949 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0695. Min Range: -5.0695
Max Act: 4.6945. Min Act: -0.1700
Data Index: 3613289 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0695. Min Range: -5.0695
Max Act: 4.6945. Min Act: -0.1700
Data Index: 2625 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19