Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3936 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0827. Min Range: -6.0827
Max Act: 6.0827. Min Act: -0.1700
Data Index: 7752673 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0827. Min Range: -6.0827
Max Act: 6.0202. Min Act: -0.1700
Data Index: 5775215 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0827. Min Range: -6.0827
Max Act: 5.9889. Min Act: -0.1700
Data Index: 4042917 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0827. Min Range: -6.0827
Max Act: 5.8952. Min Act: -0.1700
Data Index: 4323843 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0827. Min Range: -6.0827
Max Act: 5.8327. Min Act: -0.1700
Data Index: 2283597 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0827. Min Range: -6.0827
Max Act: 5.7702. Min Act: -0.1700
Data Index: 4289366 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0827. Min Range: -6.0827
Max Act: 5.7702. Min Act: -0.1700
Data Index: 1129304 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0827. Min Range: -6.0827
Max Act: 5.7702. Min Act: -0.1700
Data Index: 7411959 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0827. Min Range: -6.0827
Max Act: 5.7389. Min Act: -0.1700
Data Index: 7894656 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0827. Min Range: -6.0827
Max Act: 5.7389. Min Act: -0.1700
Data Index: 2918724 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0827. Min Range: -6.0827
Max Act: 5.7389. Min Act: -0.1700
Data Index: 578163 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0827. Min Range: -6.0827
Max Act: 5.7077. Min Act: -0.1700
Data Index: 6769178 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0827. Min Range: -6.0827
Max Act: 5.6764. Min Act: -0.1700
Data Index: 2417561 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0827. Min Range: -6.0827
Max Act: 5.6764. Min Act: -0.1700
Data Index: 820840 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0827. Min Range: -6.0827
Max Act: 5.6764. Min Act: -0.1700
Data Index: 3280743 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0827. Min Range: -6.0827
Max Act: 5.6764. Min Act: -0.1700
Data Index: 7021197 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0827. Min Range: -6.0827
Max Act: 5.6452. Min Act: -0.1700
Data Index: 5977611 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0827. Min Range: -6.0827
Max Act: 5.6452. Min Act: -0.1700
Data Index: 5571211 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0827. Min Range: -6.0827
Max Act: 5.6139. Min Act: -0.1700
Data Index: 1543738 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0827. Min Range: -6.0827
Max Act: 5.6139. Min Act: -0.1700
Data Index: 6769177 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19