Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 66 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1423. Min Range: -6.1423
Max Act: 6.1423. Min Act: -0.1700
Data Index: 6431993 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.7048. Min Act: -0.1700
Data Index: 3204516 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.6735. Min Act: -0.1700
Data Index: 6951380 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.4860. Min Act: -0.1700
Data Index: 3994012 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.5173. Min Act: -0.1700
Data Index: 5859539 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.4860. Min Act: -0.1700
Data Index: 221527 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.4235. Min Act: -0.1700
Data Index: 1492746 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.4548. Min Act: -0.1700
Data Index: 7070105 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.4548. Min Act: -0.1700
Data Index: 551073 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.3923. Min Act: -0.1700
Data Index: 1304312 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.3610. Min Act: -0.1700
Data Index: 1111570 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.3610. Min Act: -0.1700
Data Index: 3496095 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.3298. Min Act: -0.1700
Data Index: 5544949 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.2985. Min Act: -0.1700
Data Index: 359574 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.3298. Min Act: -0.1700
Data Index: 3207767 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.2985. Min Act: -0.1700
Data Index: 7357131 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.2985. Min Act: -0.1700
Data Index: 8647136 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.2985. Min Act: -0.1700
Data Index: 3796122 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.2985. Min Act: -0.1700
Data Index: 2396580 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1423. Min Range: -6.1423
Max Act: 5.2985. Min Act: -0.1700
Data Index: 3833499 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19