Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 887 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5619. Min Range: -5.5619
Max Act: 5.5619. Min Act: -0.1700
Data Index: 3623484 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5619. Min Range: -5.5619
Max Act: 5.5307. Min Act: -0.1700
Data Index: 4908683 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5619. Min Range: -5.5619
Max Act: 5.5307. Min Act: -0.1700
Data Index: 3573092 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5619. Min Range: -5.5619
Max Act: 5.4369. Min Act: -0.1700
Data Index: 3579227 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5619. Min Range: -5.5619
Max Act: 5.3432. Min Act: -0.1700
Data Index: 8076913 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5619. Min Range: -5.5619
Max Act: 5.2807. Min Act: -0.1700
Data Index: 2414649 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5619. Min Range: -5.5619
Max Act: 5.2494. Min Act: -0.1700
Data Index: 7032724 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5619. Min Range: -5.5619
Max Act: 5.2182. Min Act: -0.1700
Data Index: 1248455 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5619. Min Range: -5.5619
Max Act: 5.2182. Min Act: -0.1700
Data Index: 5121652 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5619. Min Range: -5.5619
Max Act: 5.2182. Min Act: -0.1700
Data Index: 7760275 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5619. Min Range: -5.5619
Max Act: 5.1869. Min Act: -0.1700
Data Index: 4741599 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5619. Min Range: -5.5619
Max Act: 5.1244. Min Act: -0.1700
Data Index: 3994947 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5619. Min Range: -5.5619
Max Act: 5.0932. Min Act: -0.1700
Data Index: 8456973 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5619. Min Range: -5.5619
Max Act: 5.0307. Min Act: -0.1700
Data Index: 93110 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5619. Min Range: -5.5619
Max Act: 5.0619. Min Act: -0.1700
Data Index: 7573394 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5619. Min Range: -5.5619
Max Act: 4.9994. Min Act: -0.1700
Data Index: 6765195 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5619. Min Range: -5.5619
Max Act: 4.9994. Min Act: -0.1700
Data Index: 1396530 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5619. Min Range: -5.5619
Max Act: 5.0307. Min Act: -0.1700
Data Index: 2785626 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5619. Min Range: -5.5619
Max Act: 4.9682. Min Act: -0.1700
Data Index: 7242311 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5619. Min Range: -5.5619
Max Act: 4.9369. Min Act: -0.1700
Data Index: 7702773 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19