Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3580 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.7480. Min Act: -0.1700
Data Index: 6716950 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.7168. Min Act: -0.1700
Data Index: 2132102 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.7168. Min Act: -0.1700
Data Index: 1794795 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.7168. Min Act: -0.1700
Data Index: 4767714 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.6543. Min Act: -0.1700
Data Index: 4885802 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.5918. Min Act: -0.1700
Data Index: 4875233 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.5293. Min Act: -0.1700
Data Index: 4210609 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.5605. Min Act: -0.1700
Data Index: 4521494 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.5293. Min Act: -0.1700
Data Index: 2842598 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.5293. Min Act: -0.1700
Data Index: 5366619 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.4980. Min Act: -0.1700
Data Index: 3975057 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.5293. Min Act: -0.1700
Data Index: 6683642 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.4668. Min Act: -0.1700
Data Index: 7884559 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.4668. Min Act: -0.1700
Data Index: 2510132 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.4668. Min Act: -0.1700
Data Index: 3643134 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.4668. Min Act: -0.1700
Data Index: 5619017 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.4355. Min Act: -0.1700
Data Index: 7561705 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.4355. Min Act: -0.1700
Data Index: 3987426 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.4355. Min Act: -0.1700
Data Index: 1825390 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7480. Min Range: -5.7480
Max Act: 5.4355. Min Act: -0.1700
Data Index: 3706861 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19