Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4544 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.9522. Min Act: -0.1700
Data Index: 6303040 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.7334. Min Act: -0.1700
Data Index: 8732818 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.6397. Min Act: -0.1700
Data Index: 4878372 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.3584. Min Act: -0.1700
Data Index: 602357 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.3584. Min Act: -0.1700
Data Index: 4157558 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.2334. Min Act: -0.1700
Data Index: 2830206 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.2334. Min Act: -0.1700
Data Index: 6422140 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.1397. Min Act: -0.1700
Data Index: 1497615 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.1397. Min Act: -0.1700
Data Index: 2991569 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.1084. Min Act: -0.1700
Data Index: 535937 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.1084. Min Act: -0.1700
Data Index: 3649305 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.1084. Min Act: -0.1700
Data Index: 6995172 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.1084. Min Act: -0.1700
Data Index: 2256039 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.0772. Min Act: -0.1700
Data Index: 1320508 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.0772. Min Act: -0.1700
Data Index: 5418936 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.0459. Min Act: -0.1700
Data Index: 3796503 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.0147. Min Act: -0.1700
Data Index: 4034803 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.0459. Min Act: -0.1700
Data Index: 5898959 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.0459. Min Act: -0.1700
Data Index: 1924299 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9522. Min Range: -6.9522
Max Act: 6.0459. Min Act: -0.1700
Data Index: 2562240 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19