Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1250 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3583. Min Range: -5.3583
Max Act: 5.3583. Min Act: -0.1700
Data Index: 6088012 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3583. Min Range: -5.3583
Max Act: 5.0458. Min Act: -0.1700
Data Index: 7770790 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3583. Min Range: -5.3583
Max Act: 5.0458. Min Act: -0.1700
Data Index: 6651594 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3583. Min Range: -5.3583
Max Act: 5.0458. Min Act: -0.1700
Data Index: 3360701 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3583. Min Range: -5.3583
Max Act: 5.0458. Min Act: -0.1700
Data Index: 4274564 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3583. Min Range: -5.3583
Max Act: 5.0145. Min Act: -0.1700
Data Index: 2308398 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3583. Min Range: -5.3583
Max Act: 4.9833. Min Act: -0.1700
Data Index: 4731251 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3583. Min Range: -5.3583
Max Act: 4.9833. Min Act: -0.1700
Data Index: 1496764 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3583. Min Range: -5.3583
Max Act: 4.9208. Min Act: -0.1700
Data Index: 3021600 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3583. Min Range: -5.3583
Max Act: 4.8895. Min Act: -0.1700
Data Index: 2707563 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3583. Min Range: -5.3583
Max Act: 4.8895. Min Act: -0.1700
Data Index: 252007 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3583. Min Range: -5.3583
Max Act: 4.8895. Min Act: -0.1700
Data Index: 2344788 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3583. Min Range: -5.3583
Max Act: 4.8895. Min Act: -0.1700
Data Index: 3480022 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3583. Min Range: -5.3583
Max Act: 4.9208. Min Act: -0.1700
Data Index: 5175363 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3583. Min Range: -5.3583
Max Act: 4.8895. Min Act: -0.1700
Data Index: 3202580 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3583. Min Range: -5.3583
Max Act: 4.8583. Min Act: -0.1700
Data Index: 3150812 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3583. Min Range: -5.3583
Max Act: 4.8270. Min Act: -0.1700
Data Index: 1624092 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3583. Min Range: -5.3583
Max Act: 4.8583. Min Act: -0.1700
Data Index: 1965289 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3583. Min Range: -5.3583
Max Act: 4.8583. Min Act: -0.1700
Data Index: 4381887 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3583. Min Range: -5.3583
Max Act: 4.8583. Min Act: -0.1700
Data Index: 1225112 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19