Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1971 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0540. Min Range: -5.0540
Max Act: 5.0540. Min Act: -0.1700
Data Index: 7841296 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0540. Min Range: -5.0540
Max Act: 5.0227. Min Act: -0.1700
Data Index: 690703 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0540. Min Range: -5.0540
Max Act: 4.9915. Min Act: -0.1700
Data Index: 4241089 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0540. Min Range: -5.0540
Max Act: 4.9915. Min Act: -0.1700
Data Index: 4877900 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0540. Min Range: -5.0540
Max Act: 4.9602. Min Act: -0.1700
Data Index: 4358552 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0540. Min Range: -5.0540
Max Act: 4.9602. Min Act: -0.1700
Data Index: 2903955 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0540. Min Range: -5.0540
Max Act: 4.9290. Min Act: -0.1700
Data Index: 5950223 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0540. Min Range: -5.0540
Max Act: 4.8665. Min Act: -0.1700
Data Index: 2857878 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0540. Min Range: -5.0540
Max Act: 4.8665. Min Act: -0.1700
Data Index: 3917544 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0540. Min Range: -5.0540
Max Act: 4.8352. Min Act: -0.1700
Data Index: 6199845 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0540. Min Range: -5.0540
Max Act: 4.8352. Min Act: -0.1700
Data Index: 6016601 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0540. Min Range: -5.0540
Max Act: 4.8040. Min Act: -0.1700
Data Index: 6594669 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0540. Min Range: -5.0540
Max Act: 4.8040. Min Act: -0.1700
Data Index: 6262595 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0540. Min Range: -5.0540
Max Act: 4.8040. Min Act: -0.1700
Data Index: 6140954 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0540. Min Range: -5.0540
Max Act: 4.8040. Min Act: -0.1700
Data Index: 448741 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0540. Min Range: -5.0540
Max Act: 4.8040. Min Act: -0.1700
Data Index: 8168371 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0540. Min Range: -5.0540
Max Act: 4.7415. Min Act: -0.1700
Data Index: 5950222 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0540. Min Range: -5.0540
Max Act: 4.7415. Min Act: -0.1700
Data Index: 7555906 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0540. Min Range: -5.0540
Max Act: 4.7415. Min Act: -0.1700
Data Index: 3167453 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0540. Min Range: -5.0540
Max Act: 4.7415. Min Act: -0.1700
Data Index: 744815 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19