Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6045 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.8701. Min Act: -0.1700
Data Index: 7875777 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.7138. Min Act: -0.1700
Data Index: 7101436 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.5576. Min Act: -0.1700
Data Index: 7875776 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.5263. Min Act: -0.1700
Data Index: 887322 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.5576. Min Act: -0.1700
Data Index: 7268154 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.4638. Min Act: -0.1700
Data Index: 1674552 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.3388. Min Act: -0.1700
Data Index: 4679356 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.3701. Min Act: -0.1700
Data Index: 865661 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.2763. Min Act: -0.1700
Data Index: 5783982 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.3076. Min Act: -0.1700
Data Index: 5203992 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.2763. Min Act: -0.1700
Data Index: 6870303 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.2451. Min Act: -0.1700
Data Index: 1615043 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.1826. Min Act: -0.1700
Data Index: 7438831 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.2138. Min Act: -0.1700
Data Index: 3642624 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.2138. Min Act: -0.1700
Data Index: 3183601 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.2138. Min Act: -0.1700
Data Index: 1890457 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.1513. Min Act: -0.1700
Data Index: 1382447 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.1513. Min Act: -0.1700
Data Index: 2043780 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.1513. Min Act: -0.1700
Data Index: 5932314 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8701. Min Range: -5.8701
Max Act: 5.1513. Min Act: -0.1700
Data Index: 3745669 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19