Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3866 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.5162. Min Act: -0.1700
Data Index: 5305239 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.5162. Min Act: -0.1700
Data Index: 963317 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.4849. Min Act: -0.1700
Data Index: 4119855 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.4849. Min Act: -0.1700
Data Index: 4287197 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.4849. Min Act: -0.1700
Data Index: 651925 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.4849. Min Act: -0.1700
Data Index: 534106 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.4849. Min Act: -0.1700
Data Index: 2057240 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.4535. Min Act: -0.1700
Data Index: 2764611 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.4535. Min Act: -0.1700
Data Index: 3592215 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.4535. Min Act: -0.1700
Data Index: 2472954 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.4535. Min Act: -0.1700
Data Index: 1155025 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.4535. Min Act: -0.1700
Data Index: 1136899 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.4535. Min Act: -0.1700
Data Index: 7356382 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.4535. Min Act: -0.1700
Data Index: 6411223 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.4535. Min Act: -0.1700
Data Index: 4420431 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.4222. Min Act: -0.1700
Data Index: 316790 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.4535. Min Act: -0.1700
Data Index: 3631094 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.4222. Min Act: -0.1700
Data Index: 1012197 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.4222. Min Act: -0.1700
Data Index: 593818 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5162. Min Range: -3.5162
Max Act: 3.4222. Min Act: -0.1700
Data Index: 2224191 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19