Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3102 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0290. Min Range: -4.0290
Max Act: 4.0290. Min Act: -0.1700
Data Index: 3126971 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.9978. Min Act: -0.1700
Data Index: 3734506 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.9978. Min Act: -0.1700
Data Index: 2594913 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.9665. Min Act: -0.1700
Data Index: 244784 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.9352. Min Act: -0.1700
Data Index: 8235158 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.9665. Min Act: -0.1700
Data Index: 5608549 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.9040. Min Act: -0.1700
Data Index: 8153580 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.9040. Min Act: -0.1700
Data Index: 8116252 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.8727. Min Act: -0.1700
Data Index: 2827543 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.8883. Min Act: -0.1700
Data Index: 1502002 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.8571. Min Act: -0.1700
Data Index: 2226445 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.8258. Min Act: -0.1700
Data Index: 753196 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.7945. Min Act: -0.1700
Data Index: 5505851 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.7945. Min Act: -0.1700
Data Index: 2254401 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.7945. Min Act: -0.1700
Data Index: 4073088 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.7789. Min Act: -0.1700
Data Index: 6875110 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.7632. Min Act: -0.1700
Data Index: 5033069 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.7632. Min Act: -0.1700
Data Index: 4214152 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.7476. Min Act: -0.1700
Data Index: 456945 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0290. Min Range: -4.0290
Max Act: 3.7476. Min Act: -0.1700
Data Index: 4966744 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19