Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3338 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3710. Min Range: -5.3710
Max Act: 5.3710. Min Act: -0.1700
Data Index: 1664524 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3710. Min Range: -5.3710
Max Act: 5.3085. Min Act: -0.1700
Data Index: 8556297 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3710. Min Range: -5.3710
Max Act: 5.2773. Min Act: -0.1700
Data Index: 3191371 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3710. Min Range: -5.3710
Max Act: 5.2148. Min Act: -0.1700
Data Index: 8694932 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3710. Min Range: -5.3710
Max Act: 5.1523. Min Act: -0.1700
Data Index: 4523960 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3710. Min Range: -5.3710
Max Act: 5.1523. Min Act: -0.1700
Data Index: 2139441 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3710. Min Range: -5.3710
Max Act: 5.0585. Min Act: -0.1700
Data Index: 3738345 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3710. Min Range: -5.3710
Max Act: 5.0585. Min Act: -0.1700
Data Index: 1195283 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3710. Min Range: -5.3710
Max Act: 5.0585. Min Act: -0.1700
Data Index: 1060352 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3710. Min Range: -5.3710
Max Act: 5.0585. Min Act: -0.1700
Data Index: 947346 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3710. Min Range: -5.3710
Max Act: 5.0273. Min Act: -0.1700
Data Index: 2611636 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3710. Min Range: -5.3710
Max Act: 5.0273. Min Act: -0.1700
Data Index: 5154243 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3710. Min Range: -5.3710
Max Act: 4.9960. Min Act: -0.1700
Data Index: 8579420 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3710. Min Range: -5.3710
Max Act: 4.9960. Min Act: -0.1700
Data Index: 2917860 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3710. Min Range: -5.3710
Max Act: 4.9960. Min Act: -0.1700
Data Index: 4380415 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3710. Min Range: -5.3710
Max Act: 5.0273. Min Act: -0.1700
Data Index: 5140985 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3710. Min Range: -5.3710
Max Act: 4.9960. Min Act: -0.1700
Data Index: 7373933 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3710. Min Range: -5.3710
Max Act: 4.9960. Min Act: -0.1700
Data Index: 8733937 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3710. Min Range: -5.3710
Max Act: 4.9960. Min Act: -0.1700
Data Index: 1467921 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3710. Min Range: -5.3710
Max Act: 4.9960. Min Act: -0.1700
Data Index: 3720821 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19