Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1995 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3577. Min Range: -6.3577
Max Act: 6.3577. Min Act: -0.1700
Data Index: 6165531 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3577. Min Range: -6.3577
Max Act: 6.3264. Min Act: -0.1700
Data Index: 5621261 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3577. Min Range: -6.3577
Max Act: 6.2952. Min Act: -0.1700
Data Index: 4284496 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3577. Min Range: -6.3577
Max Act: 6.2327. Min Act: -0.1700
Data Index: 5621260 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3577. Min Range: -6.3577
Max Act: 6.1702. Min Act: -0.1700
Data Index: 3776451 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3577. Min Range: -6.3577
Max Act: 6.1389. Min Act: -0.1700
Data Index: 5621264 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3577. Min Range: -6.3577
Max Act: 6.1077. Min Act: -0.1700
Data Index: 2045814 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3577. Min Range: -6.3577
Max Act: 6.0764. Min Act: -0.1700
Data Index: 6130324 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3577. Min Range: -6.3577
Max Act: 6.0764. Min Act: -0.1700
Data Index: 6165530 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3577. Min Range: -6.3577
Max Act: 6.0452. Min Act: -0.1700
Data Index: 5621263 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3577. Min Range: -6.3577
Max Act: 6.0764. Min Act: -0.1700
Data Index: 6165532 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3577. Min Range: -6.3577
Max Act: 6.0139. Min Act: -0.1700
Data Index: 6165535 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3577. Min Range: -6.3577
Max Act: 6.0139. Min Act: -0.1700
Data Index: 2813656 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3577. Min Range: -6.3577
Max Act: 6.0139. Min Act: -0.1700
Data Index: 2010524 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3577. Min Range: -6.3577
Max Act: 5.9827. Min Act: -0.1700
Data Index: 1679240 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3577. Min Range: -6.3577
Max Act: 5.9827. Min Act: -0.1700
Data Index: 5621262 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3577. Min Range: -6.3577
Max Act: 5.9514. Min Act: -0.1700
Data Index: 3163043 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3577. Min Range: -6.3577
Max Act: 5.9514. Min Act: -0.1700
Data Index: 4615255 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3577. Min Range: -6.3577
Max Act: 5.9514. Min Act: -0.1700
Data Index: 3450607 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3577. Min Range: -6.3577
Max Act: 5.9514. Min Act: -0.1700
Data Index: 2723013 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19