Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2876 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2345. Min Range: -6.2345
Max Act: 6.2345. Min Act: -0.1700
Data Index: 6335354 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2345. Min Range: -6.2345
Max Act: 6.1407. Min Act: -0.1700
Data Index: 8586791 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2345. Min Range: -6.2345
Max Act: 6.1095. Min Act: -0.1700
Data Index: 3084921 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2345. Min Range: -6.2345
Max Act: 6.0782. Min Act: -0.1700
Data Index: 2574229 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2345. Min Range: -6.2345
Max Act: 5.9845. Min Act: -0.1700
Data Index: 1248256 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2345. Min Range: -6.2345
Max Act: 5.9845. Min Act: -0.1700
Data Index: 1248255 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2345. Min Range: -6.2345
Max Act: 5.9532. Min Act: -0.1700
Data Index: 1266815 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2345. Min Range: -6.2345
Max Act: 5.9532. Min Act: -0.1700
Data Index: 5447630 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2345. Min Range: -6.2345
Max Act: 5.9220. Min Act: -0.1700
Data Index: 6335355 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2345. Min Range: -6.2345
Max Act: 5.9220. Min Act: -0.1700
Data Index: 6715700 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2345. Min Range: -6.2345
Max Act: 5.9220. Min Act: -0.1700
Data Index: 4658357 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2345. Min Range: -6.2345
Max Act: 5.9220. Min Act: -0.1700
Data Index: 8146623 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2345. Min Range: -6.2345
Max Act: 5.8907. Min Act: -0.1700
Data Index: 2474553 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2345. Min Range: -6.2345
Max Act: 5.8282. Min Act: -0.1700
Data Index: 2354275 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2345. Min Range: -6.2345
Max Act: 5.7970. Min Act: -0.1700
Data Index: 3428603 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2345. Min Range: -6.2345
Max Act: 5.8595. Min Act: -0.1700
Data Index: 722247 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2345. Min Range: -6.2345
Max Act: 5.7345. Min Act: -0.1700
Data Index: 5516805 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2345. Min Range: -6.2345
Max Act: 5.7345. Min Act: -0.1700
Data Index: 6146733 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2345. Min Range: -6.2345
Max Act: 5.7657. Min Act: -0.1700
Data Index: 8024768 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2345. Min Range: -6.2345
Max Act: 5.7345. Min Act: -0.1700
Data Index: 5212503 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19