Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2007 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1466. Min Range: -7.1466
Max Act: 7.1466. Min Act: -0.1700
Data Index: 2544239 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1466. Min Range: -7.1466
Max Act: 7.1466. Min Act: -0.1700
Data Index: 4885926 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.9904. Min Act: -0.1700
Data Index: 873308 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.8966. Min Act: -0.1700
Data Index: 1510015 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.7716. Min Act: -0.1700
Data Index: 4479168 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.7091. Min Act: -0.1700
Data Index: 3879022 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.6154. Min Act: -0.1700
Data Index: 7334411 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.5841. Min Act: -0.1700
Data Index: 7019508 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.5841. Min Act: -0.1700
Data Index: 2729498 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.4904. Min Act: -0.1700
Data Index: 3347146 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.4591. Min Act: -0.1700
Data Index: 802311 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.4591. Min Act: -0.1700
Data Index: 2914746 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.4279. Min Act: -0.1700
Data Index: 6077666 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.4279. Min Act: -0.1700
Data Index: 5187349 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.4279. Min Act: -0.1700
Data Index: 7561880 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.3966. Min Act: -0.1700
Data Index: 8783436 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.3966. Min Act: -0.1700
Data Index: 1189278 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.3966. Min Act: -0.1700
Data Index: 583992 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.3654. Min Act: -0.1700
Data Index: 1506430 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1466. Min Range: -7.1466
Max Act: 6.3029. Min Act: -0.1700
Data Index: 5362198 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19