Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.8826. Min Act: -0.1700
Data Index: 1951213 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.8201. Min Act: -0.1700
Data Index: 5687909 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.6014. Min Act: -0.1700
Data Index: 7582482 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.5389. Min Act: -0.1700
Data Index: 792060 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.5389. Min Act: -0.1700
Data Index: 2111046 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.5076. Min Act: -0.1700
Data Index: 7919455 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.4764. Min Act: -0.1700
Data Index: 1121860 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.4764. Min Act: -0.1700
Data Index: 3180584 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.4764. Min Act: -0.1700
Data Index: 7796120 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.4764. Min Act: -0.1700
Data Index: 91204 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.4764. Min Act: -0.1700
Data Index: 493438 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.4764. Min Act: -0.1700
Data Index: 1290465 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.4451. Min Act: -0.1700
Data Index: 342002 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.4451. Min Act: -0.1700
Data Index: 1659092 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.4139. Min Act: -0.1700
Data Index: 8003936 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.3826. Min Act: -0.1700
Data Index: 578387 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.3826. Min Act: -0.1700
Data Index: 3968984 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.3514. Min Act: -0.1700
Data Index: 3968974 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.3514. Min Act: -0.1700
Data Index: 4998886 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8826. Min Range: -5.8826
Max Act: 5.3514. Min Act: -0.1700
Data Index: 5971364 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19