Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2838 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0847. Min Range: -4.0847
Max Act: 4.0847. Min Act: -0.1700
Data Index: 5201765 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.9284. Min Act: -0.1700
Data Index: 2640804 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.9284. Min Act: -0.1700
Data Index: 4002967 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8658. Min Act: -0.1700
Data Index: 6384294 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8346. Min Act: -0.1700
Data Index: 8397850 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8346. Min Act: -0.1700
Data Index: 8556744 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8658. Min Act: -0.1700
Data Index: 1980940 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8346. Min Act: -0.1700
Data Index: 6101802 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8346. Min Act: -0.1700
Data Index: 5353308 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8658. Min Act: -0.1700
Data Index: 2341187 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8346. Min Act: -0.1700
Data Index: 7886902 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8346. Min Act: -0.1700
Data Index: 4957111 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8346. Min Act: -0.1700
Data Index: 4960314 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8346. Min Act: -0.1700
Data Index: 4231209 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8033. Min Act: -0.1700
Data Index: 3985777 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8346. Min Act: -0.1700
Data Index: 7838946 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8346. Min Act: -0.1700
Data Index: 5865625 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.7877. Min Act: -0.1700
Data Index: 7265327 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.7877. Min Act: -0.1700
Data Index: 7265329 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8033. Min Act: -0.1700
Data Index: 1278234 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19