Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2824 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.9314. Min Act: -0.1700
Data Index: 8105315 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.8689. Min Act: -0.1700
Data Index: 1409855 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.8689. Min Act: -0.1700
Data Index: 1220691 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.8064. Min Act: -0.1700
Data Index: 7940396 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.8064. Min Act: -0.1700
Data Index: 3067390 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.7439. Min Act: -0.1700
Data Index: 4284167 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.6814. Min Act: -0.1700
Data Index: 4644582 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.6189. Min Act: -0.1700
Data Index: 4603365 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.6814. Min Act: -0.1700
Data Index: 6850981 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.5564. Min Act: -0.1700
Data Index: 1768636 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.3689. Min Act: -0.1700
Data Index: 4283251 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.3689. Min Act: -0.1700
Data Index: 219822 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.3064. Min Act: -0.1700
Data Index: 3634138 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.3064. Min Act: -0.1700
Data Index: 2076298 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.2439. Min Act: -0.1700
Data Index: 8614381 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.3064. Min Act: -0.1700
Data Index: 901849 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.3064. Min Act: -0.1700
Data Index: 4509593 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.3064. Min Act: -0.1700
Data Index: 6790332 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.1814. Min Act: -0.1700
Data Index: 7397429 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9314. Min Range: -9.9314
Max Act: 9.1814. Min Act: -0.1700
Data Index: 106132 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19