Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3265 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0514. Min Range: -6.0514
Max Act: 6.0514. Min Act: -0.1700
Data Index: 6613027 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.8639. Min Act: -0.1700
Data Index: 7398492 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.8639. Min Act: -0.1700
Data Index: 3590164 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.8014. Min Act: -0.1700
Data Index: 6964889 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.8327. Min Act: -0.1700
Data Index: 163086 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.8014. Min Act: -0.1700
Data Index: 3682245 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.8014. Min Act: -0.1700
Data Index: 7960568 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.7702. Min Act: -0.1700
Data Index: 5123001 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.7389. Min Act: -0.1700
Data Index: 2623532 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.7389. Min Act: -0.1700
Data Index: 1350541 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.7077. Min Act: -0.1700
Data Index: 4024582 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.7077. Min Act: -0.1700
Data Index: 885468 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.7077. Min Act: -0.1699
Data Index: 7932050 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.7077. Min Act: -0.1700
Data Index: 3846063 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.7077. Min Act: -0.1700
Data Index: 6757092 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.6452. Min Act: -0.1700
Data Index: 6362463 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.6764. Min Act: -0.1700
Data Index: 1781 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.6764. Min Act: -0.1700
Data Index: 6362464 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.6764. Min Act: -0.1700
Data Index: 67211 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0514. Min Range: -6.0514
Max Act: 5.6764. Min Act: -0.1700
Data Index: 2195200 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19