Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2992 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1766. Min Range: -7.1766
Max Act: 7.1766. Min Act: -0.1700
Data Index: 4231339 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1766. Min Range: -7.1766
Max Act: 7.1141. Min Act: -0.1700
Data Index: 827999 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1766. Min Range: -7.1766
Max Act: 6.9891. Min Act: -0.1700
Data Index: 4368174 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1766. Min Range: -7.1766
Max Act: 7.0203. Min Act: -0.1700
Data Index: 8596249 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1766. Min Range: -7.1766
Max Act: 6.9578. Min Act: -0.1700
Data Index: 6584368 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1766. Min Range: -7.1766
Max Act: 6.8641. Min Act: -0.1700
Data Index: 7135086 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1766. Min Range: -7.1766
Max Act: 6.8328. Min Act: -0.1700
Data Index: 8407100 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1766. Min Range: -7.1766
Max Act: 6.8016. Min Act: -0.1700
Data Index: 8288461 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1766. Min Range: -7.1766
Max Act: 6.8328. Min Act: -0.1700
Data Index: 1682242 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1766. Min Range: -7.1766
Max Act: 6.8328. Min Act: -0.1700
Data Index: 5206682 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1766. Min Range: -7.1766
Max Act: 6.8016. Min Act: -0.1700
Data Index: 4620404 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1766. Min Range: -7.1766
Max Act: 6.7703. Min Act: -0.1700
Data Index: 1637485 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1766. Min Range: -7.1766
Max Act: 6.7703. Min Act: -0.1700
Data Index: 5941045 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1766. Min Range: -7.1766
Max Act: 6.7703. Min Act: -0.1700
Data Index: 1088616 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1766. Min Range: -7.1766
Max Act: 6.7703. Min Act: -0.1700
Data Index: 6273441 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1766. Min Range: -7.1766
Max Act: 6.7391. Min Act: -0.1700
Data Index: 5133804 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1766. Min Range: -7.1766
Max Act: 6.7391. Min Act: -0.1700
Data Index: 830558 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1766. Min Range: -7.1766
Max Act: 6.7391. Min Act: -0.1700
Data Index: 3350766 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1766. Min Range: -7.1766
Max Act: 6.7078. Min Act: -0.1700
Data Index: 6237321 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1766. Min Range: -7.1766
Max Act: 6.7078. Min Act: -0.1700
Data Index: 7313461 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19