Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3062 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9886. Min Act: -0.1700
Data Index: 2342231 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 5191702 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 3684560 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 4400276 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 3143582 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 2596705 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 2552664 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 4511292 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 1367823 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 716341 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 5274070 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 3110618 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 1699102 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 1963295 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 2980539 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 4583304 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 1068635 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 1670917 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 4759616 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 5371930 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19