Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3521 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.4448. Min Act: -0.1700
Data Index: 5124661 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.4136. Min Act: -0.1700
Data Index: 1713444 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.3823. Min Act: -0.1700
Data Index: 4131860 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.3511. Min Act: -0.1700
Data Index: 6224505 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.3511. Min Act: -0.1700
Data Index: 1545870 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.3511. Min Act: -0.1700
Data Index: 930318 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.3823. Min Act: -0.1700
Data Index: 280168 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.3511. Min Act: -0.1700
Data Index: 3313224 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.3511. Min Act: -0.1700
Data Index: 1896012 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.3511. Min Act: -0.1700
Data Index: 6194115 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.3511. Min Act: -0.1699
Data Index: 3151804 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.3511. Min Act: -0.1700
Data Index: 3757325 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.3198. Min Act: -0.1700
Data Index: 364164 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.3198. Min Act: -0.1700
Data Index: 2056556 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.3198. Min Act: -0.1700
Data Index: 8161720 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.3198. Min Act: -0.1700
Data Index: 1814078 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.2886. Min Act: -0.1700
Data Index: 429449 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.3198. Min Act: -0.1700
Data Index: 1076789 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.2886. Min Act: -0.1700
Data Index: 4419430 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4448. Min Range: -4.4448
Max Act: 4.2886. Min Act: -0.1700
Data Index: 582456 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19