Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4809 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.4543. Min Act: -0.1700
Data Index: 3807345 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.4857. Min Act: -0.1700
Data Index: 3036323 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.4543. Min Act: -0.1700
Data Index: 8305955 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.4230. Min Act: -0.1700
Data Index: 8448140 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.4230. Min Act: -0.1700
Data Index: 8732949 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.3917. Min Act: -0.1700
Data Index: 6262947 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.3917. Min Act: -0.1700
Data Index: 4152909 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.4230. Min Act: -0.1700
Data Index: 7384493 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.3917. Min Act: -0.1700
Data Index: 7487517 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.3603. Min Act: -0.1700
Data Index: 4053079 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.3917. Min Act: -0.1700
Data Index: 5284321 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.3917. Min Act: -0.1700
Data Index: 2189995 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.3917. Min Act: -0.1700
Data Index: 4009211 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.3917. Min Act: -0.1700
Data Index: 3183575 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.3603. Min Act: -0.1700
Data Index: 4181835 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.3289. Min Act: -0.1700
Data Index: 3392654 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.3289. Min Act: -0.1700
Data Index: 3421297 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.3603. Min Act: -0.1700
Data Index: 4470711 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.3289. Min Act: -0.1700
Data Index: 1881565 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4857. Min Range: -3.4857
Max Act: 3.3603. Min Act: -0.1700
Data Index: 3487291 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19