Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3509 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.2583. Min Act: -0.1700
Data Index: 2848015 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.2270. Min Act: -0.1700
Data Index: 8593833 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.2270. Min Act: -0.1700
Data Index: 3151048 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.2270. Min Act: -0.1700
Data Index: 6743901 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.1958. Min Act: -0.1700
Data Index: 8315769 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.1645. Min Act: -0.1700
Data Index: 3209969 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.1645. Min Act: -0.1700
Data Index: 1573560 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.1645. Min Act: -0.1700
Data Index: 7563223 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.1645. Min Act: -0.1700
Data Index: 5135338 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.1645. Min Act: -0.1700
Data Index: 716278 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.1645. Min Act: -0.1700
Data Index: 7318252 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.1645. Min Act: -0.1700
Data Index: 6578008 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.1645. Min Act: -0.1700
Data Index: 3591353 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.1645. Min Act: -0.1700
Data Index: 6106953 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.1645. Min Act: -0.1700
Data Index: 5846636 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.1645. Min Act: -0.1700
Data Index: 5837824 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.1645. Min Act: -0.1700
Data Index: 6609414 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.1645. Min Act: -0.1700
Data Index: 5514957 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.1645. Min Act: -0.1700
Data Index: 4034991 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.1333. Min Act: -0.1700
Data Index: 5279465 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19