Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1599 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.6901. Min Act: -0.1700
Data Index: 8705395 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.6276. Min Act: -0.1700
Data Index: 2095001 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.5963. Min Act: -0.1700
Data Index: 850592 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.5963. Min Act: -0.1700
Data Index: 7904709 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.5963. Min Act: -0.1700
Data Index: 7472295 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.5651. Min Act: -0.1700
Data Index: 1918268 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.5963. Min Act: -0.1700
Data Index: 3960641 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.5651. Min Act: -0.1700
Data Index: 2137490 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.5651. Min Act: -0.1700
Data Index: 7538553 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.5963. Min Act: -0.1700
Data Index: 5755127 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.5338. Min Act: -0.1700
Data Index: 1334358 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.5338. Min Act: -0.1700
Data Index: 1469231 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.5338. Min Act: -0.1700
Data Index: 2997522 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.5338. Min Act: -0.1700
Data Index: 4387877 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.5338. Min Act: -0.1700
Data Index: 6926959 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.5026. Min Act: -0.1700
Data Index: 4603914 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.5026. Min Act: -0.1700
Data Index: 7226823 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.5026. Min Act: -0.1700
Data Index: 875966 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.5338. Min Act: -0.1700
Data Index: 6228860 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6901. Min Range: -6.6901
Max Act: 6.5026. Min Act: -0.1700
Data Index: 6015177 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19