Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2650 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4437. Min Range: -5.4437
Max Act: 5.4437. Min Act: -0.1700
Data Index: 7706565 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.9124. Min Act: -0.1700
Data Index: 5950193 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.8812. Min Act: -0.1700
Data Index: 8508948 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.7874. Min Act: -0.1700
Data Index: 5073643 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.8499. Min Act: -0.1700
Data Index: 1178540 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.8187. Min Act: -0.1700
Data Index: 1383385 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.7562. Min Act: -0.1700
Data Index: 7790577 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.6937. Min Act: -0.1700
Data Index: 983728 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.7562. Min Act: -0.1700
Data Index: 1924661 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.7562. Min Act: -0.1700
Data Index: 341302 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.6937. Min Act: -0.1700
Data Index: 8584116 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.6937. Min Act: -0.1700
Data Index: 4770649 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.6624. Min Act: -0.1700
Data Index: 1815370 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.6937. Min Act: -0.1700
Data Index: 6059332 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.6937. Min Act: -0.1700
Data Index: 4856800 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.6937. Min Act: -0.1700
Data Index: 2000330 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.6937. Min Act: -0.1700
Data Index: 1332972 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.6937. Min Act: -0.1700
Data Index: 529605 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.6937. Min Act: -0.1700
Data Index: 1407513 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4437. Min Range: -5.4437
Max Act: 4.6624. Min Act: -0.1700
Data Index: 4930915 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19