Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2771 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.8505. Min Act: -0.1700
Data Index: 6952060 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.7567. Min Act: -0.1700
Data Index: 3490243 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.7255. Min Act: -0.1700
Data Index: 7179744 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.6317. Min Act: -0.1700
Data Index: 2833578 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.6942. Min Act: -0.1700
Data Index: 2132490 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.6005. Min Act: -0.1700
Data Index: 1654932 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.6005. Min Act: -0.1700
Data Index: 1520289 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.6005. Min Act: -0.1700
Data Index: 6759218 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.5067. Min Act: -0.1700
Data Index: 3930475 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.6005. Min Act: -0.1700
Data Index: 3383873 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.5380. Min Act: -0.1700
Data Index: 3336496 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.5380. Min Act: -0.1700
Data Index: 1314609 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.5067. Min Act: -0.1700
Data Index: 1137105 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.5067. Min Act: -0.1700
Data Index: 2165920 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.5380. Min Act: -0.1700
Data Index: 7032620 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.4442. Min Act: -0.1700
Data Index: 6675848 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.4755. Min Act: -0.1700
Data Index: 6294062 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.5067. Min Act: -0.1700
Data Index: 8345192 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.5067. Min Act: -0.1700
Data Index: 7708207 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8505. Min Range: -5.8505
Max Act: 5.5067. Min Act: -0.1700
Data Index: 2159804 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19