Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3260 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.4326. Min Act: -0.1700
Data Index: 106143 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.4326. Min Act: -0.1698
Data Index: 4187916 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.4013. Min Act: -0.1699
Data Index: 7237638 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.4013. Min Act: -0.1700
Data Index: 81916 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.3701. Min Act: -0.1700
Data Index: 8423013 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.3701. Min Act: -0.1700
Data Index: 8309915 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.3075. Min Act: -0.1700
Data Index: 6590713 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.3075. Min Act: -0.1700
Data Index: 7065732 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.2763. Min Act: -0.1700
Data Index: 560239 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.3075. Min Act: -0.1697
Data Index: 7663521 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.2763. Min Act: -0.1700
Data Index: 1218790 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.2763. Min Act: -0.1700
Data Index: 1306416 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.3075. Min Act: -0.1700
Data Index: 2845247 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.2763. Min Act: -0.1700
Data Index: 4398519 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.2763. Min Act: -0.1700
Data Index: 349405 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.2763. Min Act: -0.1700
Data Index: 2953019 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.2450. Min Act: -0.1700
Data Index: 1146324 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.2450. Min Act: -0.1700
Data Index: 5562421 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.2450. Min Act: -0.1700
Data Index: 3900255 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4326. Min Range: -4.4326
Max Act: 4.2138. Min Act: -0.1700
Data Index: 4960070 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19