Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3878 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.9929. Min Act: -0.1700
Data Index: 5039586 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0241. Min Range: -6.0241
Max Act: 6.0241. Min Act: -0.1700
Data Index: 3214522 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.8991. Min Act: -0.1700
Data Index: 3602610 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.8991. Min Act: -0.1700
Data Index: 558777 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.9304. Min Act: -0.1700
Data Index: 2854539 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.7741. Min Act: -0.1700
Data Index: 2785818 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.8054. Min Act: -0.1700
Data Index: 4078598 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.8054. Min Act: -0.1700
Data Index: 5815364 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.7429. Min Act: -0.1700
Data Index: 2264132 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.6804. Min Act: -0.1700
Data Index: 1488441 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.7429. Min Act: -0.1700
Data Index: 6237400 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.7116. Min Act: -0.1700
Data Index: 8444813 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.7116. Min Act: -0.1700
Data Index: 8379519 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.7116. Min Act: -0.1700
Data Index: 5342782 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.7116. Min Act: -0.1700
Data Index: 6661162 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.7429. Min Act: -0.1700
Data Index: 6769762 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.7429. Min Act: -0.1700
Data Index: 4891390 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.6804. Min Act: -0.1700
Data Index: 592155 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.6804. Min Act: -0.1700
Data Index: 6942616 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0241. Min Range: -6.0241
Max Act: 5.6804. Min Act: -0.1700
Data Index: 7913743 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19