Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 319470 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 2831399 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 2008352 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 2720753 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 1046902 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 3392027 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 1959711 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 322313 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 2552121 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 3722984 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 1080900 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 2501200 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 2383113 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 3139873 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 2859286 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 741822 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 5298515 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 1113113 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 3191528 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6466. Min Range: -3.6466
Max Act: 3.6466. Min Act: -0.1700
Data Index: 509020 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19