Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3810 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.1441. Min Act: -0.1700
Data Index: 7766717 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.1128. Min Act: -0.1700
Data Index: 6013402 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0816. Min Act: -0.1700
Data Index: 5655894 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0816. Min Act: -0.1700
Data Index: 6972548 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0816. Min Act: -0.1700
Data Index: 5890511 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0816. Min Act: -0.1700
Data Index: 3903155 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0503. Min Act: -0.1700
Data Index: 3002746 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0503. Min Act: -0.1700
Data Index: 4329361 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0503. Min Act: -0.1700
Data Index: 1328584 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0503. Min Act: -0.1700
Data Index: 5311309 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0503. Min Act: -0.1700
Data Index: 2836514 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0503. Min Act: -0.1700
Data Index: 2801950 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0191. Min Act: -0.1700
Data Index: 2511796 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0191. Min Act: -0.1700
Data Index: 6284052 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0503. Min Act: -0.1700
Data Index: 1624792 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0503. Min Act: -0.1700
Data Index: 6541630 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0503. Min Act: -0.1700
Data Index: 1627506 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0503. Min Act: -0.1700
Data Index: 6606723 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0503. Min Act: -0.1700
Data Index: 1646078 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1441. Min Range: -4.1441
Max Act: 4.0503. Min Act: -0.1700
Data Index: 293824 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19