Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 688 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0520. Min Range: -5.0520
Max Act: 5.0207. Min Act: -0.1700
Data Index: 3162426 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0520. Min Range: -5.0520
Max Act: 5.0520. Min Act: -0.1700
Data Index: 4755791 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0520. Min Range: -5.0520
Max Act: 4.9270. Min Act: -0.1700
Data Index: 173491 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0520. Min Range: -5.0520
Max Act: 4.8957. Min Act: -0.1700
Data Index: 1531668 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0520. Min Range: -5.0520
Max Act: 4.8332. Min Act: -0.1700
Data Index: 4974035 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0520. Min Range: -5.0520
Max Act: 4.8332. Min Act: -0.1700
Data Index: 7401663 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0520. Min Range: -5.0520
Max Act: 4.8332. Min Act: -0.1700
Data Index: 6313896 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0520. Min Range: -5.0520
Max Act: 4.8020. Min Act: -0.1700
Data Index: 1054077 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0520. Min Range: -5.0520
Max Act: 4.8020. Min Act: -0.1700
Data Index: 2389940 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0520. Min Range: -5.0520
Max Act: 4.8020. Min Act: -0.1700
Data Index: 1183517 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0520. Min Range: -5.0520
Max Act: 4.7707. Min Act: -0.1700
Data Index: 7365733 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0520. Min Range: -5.0520
Max Act: 4.7395. Min Act: -0.1700
Data Index: 4102281 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0520. Min Range: -5.0520
Max Act: 4.7082. Min Act: -0.1700
Data Index: 8024519 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0520. Min Range: -5.0520
Max Act: 4.7082. Min Act: -0.1700
Data Index: 2251774 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0520. Min Range: -5.0520
Max Act: 4.7082. Min Act: -0.1700
Data Index: 511976 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0520. Min Range: -5.0520
Max Act: 4.6770. Min Act: -0.1700
Data Index: 8382889 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0520. Min Range: -5.0520
Max Act: 4.6770. Min Act: -0.1700
Data Index: 928501 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0520. Min Range: -5.0520
Max Act: 4.6145. Min Act: -0.1700
Data Index: 6140115 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0520. Min Range: -5.0520
Max Act: 4.6145. Min Act: -0.1700
Data Index: 3042807 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0520. Min Range: -5.0520
Max Act: 4.6457. Min Act: -0.1700
Data Index: 1283316 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19