Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1650 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3832. Min Range: -6.3832
Max Act: 6.3832. Min Act: -0.1700
Data Index: 3717942 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3832. Min Range: -6.3832
Max Act: 6.3207. Min Act: -0.1700
Data Index: 3519715 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3832. Min Range: -6.3832
Max Act: 6.2582. Min Act: -0.1700
Data Index: 2956674 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3832. Min Range: -6.3832
Max Act: 6.0707. Min Act: -0.1700
Data Index: 91315 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3832. Min Range: -6.3832
Max Act: 6.0082. Min Act: -0.1700
Data Index: 8173946 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3832. Min Range: -6.3832
Max Act: 6.0082. Min Act: -0.1700
Data Index: 960642 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3832. Min Range: -6.3832
Max Act: 6.0082. Min Act: -0.1700
Data Index: 1599302 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3832. Min Range: -6.3832
Max Act: 5.9769. Min Act: -0.1700
Data Index: 2873993 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3832. Min Range: -6.3832
Max Act: 5.9457. Min Act: -0.1700
Data Index: 8319688 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3832. Min Range: -6.3832
Max Act: 5.9457. Min Act: -0.1700
Data Index: 469634 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3832. Min Range: -6.3832
Max Act: 5.9144. Min Act: -0.1700
Data Index: 4032615 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3832. Min Range: -6.3832
Max Act: 5.8832. Min Act: -0.1700
Data Index: 6787658 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3832. Min Range: -6.3832
Max Act: 5.8832. Min Act: -0.1700
Data Index: 4412856 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3832. Min Range: -6.3832
Max Act: 5.8832. Min Act: -0.1700
Data Index: 4033942 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3832. Min Range: -6.3832
Max Act: 5.8519. Min Act: -0.1700
Data Index: 1434504 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3832. Min Range: -6.3832
Max Act: 5.8519. Min Act: -0.1700
Data Index: 6010257 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3832. Min Range: -6.3832
Max Act: 5.8519. Min Act: -0.1700
Data Index: 2247158 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3832. Min Range: -6.3832
Max Act: 5.8207. Min Act: -0.1700
Data Index: 3458360 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3832. Min Range: -6.3832
Max Act: 5.7894. Min Act: -0.1700
Data Index: 6194655 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3832. Min Range: -6.3832
Max Act: 5.7582. Min Act: -0.1700
Data Index: 2731925 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19