Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 64 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4669. Min Range: -4.4669
Max Act: 4.4669. Min Act: -0.1700
Data Index: 2326072 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4669. Min Range: -4.4669
Max Act: 4.3419. Min Act: -0.1700
Data Index: 3376992 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4669. Min Range: -4.4669
Max Act: 4.2482. Min Act: -0.1700
Data Index: 4445021 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4669. Min Range: -4.4669
Max Act: 4.2794. Min Act: -0.1700
Data Index: 5561172 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4669. Min Range: -4.4669
Max Act: 4.0919. Min Act: -0.1700
Data Index: 3506215 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4669. Min Range: -4.4669
Max Act: 4.0606. Min Act: -0.1700
Data Index: 6208421 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4669. Min Range: -4.4669
Max Act: 4.0606. Min Act: -0.1700
Data Index: 8666247 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4669. Min Range: -4.4669
Max Act: 4.0606. Min Act: -0.1700
Data Index: 4974443 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4669. Min Range: -4.4669
Max Act: 4.0294. Min Act: -0.1700
Data Index: 3561186 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4669. Min Range: -4.4669
Max Act: 4.0294. Min Act: -0.1700
Data Index: 2361427 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4669. Min Range: -4.4669
Max Act: 4.0294. Min Act: -0.1700
Data Index: 1105837 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4669. Min Range: -4.4669
Max Act: 3.9981. Min Act: -0.1700
Data Index: 4261338 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4669. Min Range: -4.4669
Max Act: 3.9981. Min Act: -0.1700
Data Index: 5561175 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4669. Min Range: -4.4669
Max Act: 3.9356. Min Act: -0.1700
Data Index: 5561168 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4669. Min Range: -4.4669
Max Act: 3.9669. Min Act: -0.1700
Data Index: 4544594 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4669. Min Range: -4.4669
Max Act: 3.9356. Min Act: -0.1700
Data Index: 7854330 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4669. Min Range: -4.4669
Max Act: 3.9356. Min Act: -0.1700
Data Index: 1609776 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4669. Min Range: -4.4669
Max Act: 3.9669. Min Act: -0.1700
Data Index: 4444239 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4669. Min Range: -4.4669
Max Act: 3.9669. Min Act: -0.1700
Data Index: 1262606 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4669. Min Range: -4.4669
Max Act: 3.9669. Min Act: -0.1700
Data Index: 5561171 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19