Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 55 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1711. Min Range: -5.1711
Max Act: 5.1711. Min Act: -0.1700
Data Index: 4278483 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1711. Min Range: -5.1711
Max Act: 5.0461. Min Act: -0.1700
Data Index: 2940315 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1711. Min Range: -5.1711
Max Act: 5.0461. Min Act: -0.1700
Data Index: 8072800 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1711. Min Range: -5.1711
Max Act: 5.0149. Min Act: -0.1700
Data Index: 1418049 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1711. Min Range: -5.1711
Max Act: 4.9836. Min Act: -0.1700
Data Index: 469709 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1711. Min Range: -5.1711
Max Act: 4.9836. Min Act: -0.1700
Data Index: 6706330 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1711. Min Range: -5.1711
Max Act: 4.9524. Min Act: -0.1700
Data Index: 6844573 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1711. Min Range: -5.1711
Max Act: 4.9524. Min Act: -0.1700
Data Index: 4361099 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1711. Min Range: -5.1711
Max Act: 4.9524. Min Act: -0.1700
Data Index: 2579466 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1711. Min Range: -5.1711
Max Act: 4.9524. Min Act: -0.1700
Data Index: 7420187 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1711. Min Range: -5.1711
Max Act: 4.9211. Min Act: -0.1700
Data Index: 4705424 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1711. Min Range: -5.1711
Max Act: 4.9211. Min Act: -0.1700
Data Index: 3204873 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1711. Min Range: -5.1711
Max Act: 4.8899. Min Act: -0.1700
Data Index: 5789122 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1711. Min Range: -5.1711
Max Act: 4.8899. Min Act: -0.1700
Data Index: 5146204 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1711. Min Range: -5.1711
Max Act: 4.8899. Min Act: -0.1700
Data Index: 2886176 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1711. Min Range: -5.1711
Max Act: 4.8586. Min Act: -0.1700
Data Index: 4496690 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1711. Min Range: -5.1711
Max Act: 4.8586. Min Act: -0.1700
Data Index: 1781796 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1711. Min Range: -5.1711
Max Act: 4.8274. Min Act: -0.1700
Data Index: 3505367 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1711. Min Range: -5.1711
Max Act: 4.7961. Min Act: -0.1700
Data Index: 3872228 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1711. Min Range: -5.1711
Max Act: 4.8586. Min Act: -0.1700
Data Index: 5295497 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19