Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1561 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.8237. Min Act: -0.1700
Data Index: 5502315 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.8237. Min Act: -0.1700
Data Index: 1017632 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.7612. Min Act: -0.1700
Data Index: 3883586 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.7300. Min Act: -0.1700
Data Index: 742524 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.6675. Min Act: -0.1700
Data Index: 2332094 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.7300. Min Act: -0.1700
Data Index: 6556714 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.6362. Min Act: -0.1700
Data Index: 6689725 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.6050. Min Act: -0.1700
Data Index: 4481358 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.5425. Min Act: -0.1700
Data Index: 7068491 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.5112. Min Act: -0.1700
Data Index: 3658530 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.5112. Min Act: -0.1700
Data Index: 3690516 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.4800. Min Act: -0.1700
Data Index: 3088859 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.4487. Min Act: -0.1700
Data Index: 2945317 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.4175. Min Act: -0.1700
Data Index: 4225640 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.3862. Min Act: -0.1700
Data Index: 8701587 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.3550. Min Act: -0.1700
Data Index: 3285001 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.3550. Min Act: -0.1700
Data Index: 7953090 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.3550. Min Act: -0.1700
Data Index: 922693 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.3550. Min Act: -0.1700
Data Index: 7725762 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8237. Min Range: -5.8237
Max Act: 5.3550. Min Act: -0.1700
Data Index: 6364953 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19