Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3802 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.3691. Min Act: -0.1700
Data Index: 574299 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.3377. Min Act: -0.1700
Data Index: 8545082 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.3377. Min Act: -0.1700
Data Index: 1848204 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.3063. Min Act: -0.1700
Data Index: 7040731 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.3063. Min Act: -0.1700
Data Index: 4663539 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.3063. Min Act: -0.1700
Data Index: 394325 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.3063. Min Act: -0.1700
Data Index: 1823898 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.3063. Min Act: -0.1700
Data Index: 1840957 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.2749. Min Act: -0.1700
Data Index: 3761080 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.2749. Min Act: -0.1700
Data Index: 90805 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.2435. Min Act: -0.1700
Data Index: 292174 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.3063. Min Act: -0.1700
Data Index: 3890875 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.2749. Min Act: -0.1700
Data Index: 3869508 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.2749. Min Act: -0.1700
Data Index: 3782473 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.2749. Min Act: -0.1700
Data Index: 3319899 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.2749. Min Act: -0.1700
Data Index: 2828832 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.2749. Min Act: -0.1700
Data Index: 1141506 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.2749. Min Act: -0.1700
Data Index: 1878672 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.2749. Min Act: -0.1700
Data Index: 2676905 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3691. Min Range: -3.3691
Max Act: 3.2749. Min Act: -0.1700
Data Index: 1479161 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19