Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 63 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.6582. Min Act: -0.1700
Data Index: 6489261 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.6261. Min Act: -0.1700
Data Index: 3513087 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.6100. Min Act: -0.1700
Data Index: 8386320 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.6261. Min Act: -0.1700
Data Index: 8087254 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.5939. Min Act: -0.1700
Data Index: 286012 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.5617. Min Act: -0.1700
Data Index: 8365167 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.5294. Min Act: -0.1700
Data Index: 4671325 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.5455. Min Act: -0.1700
Data Index: 8794918 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.5455. Min Act: -0.1700
Data Index: 3246047 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.5455. Min Act: -0.1700
Data Index: 6580536 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.5455. Min Act: -0.1700
Data Index: 947098 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.5294. Min Act: -0.1700
Data Index: 7975695 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.5294. Min Act: -0.1700
Data Index: 7120757 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.5294. Min Act: -0.1700
Data Index: 295558 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.5294. Min Act: -0.1700
Data Index: 1411854 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.5294. Min Act: -0.1700
Data Index: 6720325 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.5294. Min Act: -0.1700
Data Index: 2742576 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.5294. Min Act: -0.1700
Data Index: 5979179 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.5132. Min Act: -0.1700
Data Index: 2174401 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6582. Min Range: -2.6582
Max Act: 2.5132. Min Act: -0.1700
Data Index: 402064 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19