Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5254 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.8995. Min Act: -0.1700
Data Index: 7585909 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.7745. Min Act: -0.1700
Data Index: 5065654 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.7120. Min Act: -0.1700
Data Index: 8467627 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.6182. Min Act: -0.1700
Data Index: 4134119 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.6182. Min Act: -0.1700
Data Index: 8467628 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.5245. Min Act: -0.1700
Data Index: 6135440 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.4307. Min Act: -0.1700
Data Index: 7038157 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.4307. Min Act: -0.1700
Data Index: 3857882 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.3995. Min Act: -0.1700
Data Index: 2407355 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.3995. Min Act: -0.1700
Data Index: 4722947 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.3682. Min Act: -0.1700
Data Index: 8467624 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.3682. Min Act: -0.1700
Data Index: 3833625 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.3370. Min Act: -0.1700
Data Index: 8467629 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.3682. Min Act: -0.1700
Data Index: 8467626 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.3682. Min Act: -0.1700
Data Index: 7273540 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.3057. Min Act: -0.1700
Data Index: 8548442 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.3370. Min Act: -0.1700
Data Index: 8307493 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.3057. Min Act: -0.1700
Data Index: 1947728 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.3057. Min Act: -0.1700
Data Index: 281618 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8995. Min Range: -5.8995
Max Act: 5.2432. Min Act: -0.1700
Data Index: 3048602 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19