Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2845 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1624. Min Range: -9.1624
Max Act: 9.1624. Min Act: -0.1700
Data Index: 3106853 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1624. Min Range: -9.1624
Max Act: 9.1624. Min Act: -0.1700
Data Index: 2212800 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1624. Min Range: -9.1624
Max Act: 8.9124. Min Act: -0.1700
Data Index: 7266042 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1624. Min Range: -9.1624
Max Act: 8.9124. Min Act: -0.1700
Data Index: 6166670 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1624. Min Range: -9.1624
Max Act: 8.9124. Min Act: -0.1700
Data Index: 6604552 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1624. Min Range: -9.1624
Max Act: 8.8499. Min Act: -0.1700
Data Index: 168107 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1624. Min Range: -9.1624
Max Act: 8.7874. Min Act: -0.1700
Data Index: 943733 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1624. Min Range: -9.1624
Max Act: 8.7249. Min Act: -0.1700
Data Index: 121412 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1624. Min Range: -9.1624
Max Act: 8.6624. Min Act: -0.1700
Data Index: 8676113 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1624. Min Range: -9.1624
Max Act: 8.6624. Min Act: -0.1700
Data Index: 5727320 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1624. Min Range: -9.1624
Max Act: 8.6624. Min Act: -0.1700
Data Index: 8705358 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1624. Min Range: -9.1624
Max Act: 8.5999. Min Act: -0.1700
Data Index: 3719979 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1624. Min Range: -9.1624
Max Act: 8.5999. Min Act: -0.1700
Data Index: 5563715 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1624. Min Range: -9.1624
Max Act: 8.5374. Min Act: -0.1700
Data Index: 4917089 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1624. Min Range: -9.1624
Max Act: 8.5374. Min Act: -0.1700
Data Index: 6974528 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1624. Min Range: -9.1624
Max Act: 8.4749. Min Act: -0.1700
Data Index: 7506321 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1624. Min Range: -9.1624
Max Act: 8.4749. Min Act: -0.1700
Data Index: 8564310 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1624. Min Range: -9.1624
Max Act: 8.4124. Min Act: -0.1700
Data Index: 4923524 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1624. Min Range: -9.1624
Max Act: 8.4749. Min Act: -0.1700
Data Index: 80141 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1624. Min Range: -9.1624
Max Act: 8.4124. Min Act: -0.1700
Data Index: 2185696 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19