Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2773 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.8438. Min Act: -0.1700
Data Index: 2605086 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.7483. Min Act: -0.1700
Data Index: 5819310 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.7642. Min Act: -0.1700
Data Index: 5158853 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.7642. Min Act: -0.1700
Data Index: 1167874 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.7642. Min Act: -0.1699
Data Index: 5253968 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.7483. Min Act: -0.1700
Data Index: 5933580 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.7323. Min Act: -0.1700
Data Index: 1939662 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.7163. Min Act: -0.1700
Data Index: 7113893 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.7163. Min Act: -0.1700
Data Index: 5254005 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.7003. Min Act: -0.1700
Data Index: 1471417 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.6843. Min Act: -0.1700
Data Index: 2741748 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.6683. Min Act: -0.1700
Data Index: 8427634 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.6843. Min Act: -0.1700
Data Index: 1939657 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.6843. Min Act: -0.1700
Data Index: 1028764 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.6683. Min Act: -0.1700
Data Index: 400682 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.6523. Min Act: -0.1700
Data Index: 5471143 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.6362. Min Act: -0.1700
Data Index: 2655338 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.6523. Min Act: -0.1700
Data Index: 2655351 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.6362. Min Act: -0.1700
Data Index: 2482972 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8438. Min Range: -2.8438
Max Act: 2.6523. Min Act: -0.1700
Data Index: 1931908 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19