Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2748 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6827. Min Range: -7.6827
Max Act: 7.6827. Min Act: -0.1700
Data Index: 3919309 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6827. Min Range: -7.6827
Max Act: 7.5577. Min Act: -0.1700
Data Index: 7705757 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6827. Min Range: -7.6827
Max Act: 7.4952. Min Act: -0.1700
Data Index: 6297480 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6827. Min Range: -7.6827
Max Act: 7.4952. Min Act: -0.1700
Data Index: 137069 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6827. Min Range: -7.6827
Max Act: 7.4640. Min Act: -0.1700
Data Index: 6671832 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6827. Min Range: -7.6827
Max Act: 7.3702. Min Act: -0.1700
Data Index: 2791315 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6827. Min Range: -7.6827
Max Act: 7.2765. Min Act: -0.1700
Data Index: 5758440 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6827. Min Range: -7.6827
Max Act: 7.1827. Min Act: -0.1700
Data Index: 2642575 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6827. Min Range: -7.6827
Max Act: 7.1515. Min Act: -0.1700
Data Index: 1624883 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6827. Min Range: -7.6827
Max Act: 7.1202. Min Act: -0.1700
Data Index: 3987767 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6827. Min Range: -7.6827
Max Act: 7.1202. Min Act: -0.1700
Data Index: 4140381 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6827. Min Range: -7.6827
Max Act: 7.0890. Min Act: -0.1700
Data Index: 3687803 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6827. Min Range: -7.6827
Max Act: 7.0890. Min Act: -0.1700
Data Index: 7902618 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6827. Min Range: -7.6827
Max Act: 7.0265. Min Act: -0.1700
Data Index: 7507508 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6827. Min Range: -7.6827
Max Act: 6.9952. Min Act: -0.1700
Data Index: 137064 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6827. Min Range: -7.6827
Max Act: 6.9640. Min Act: -0.1700
Data Index: 8493950 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6827. Min Range: -7.6827
Max Act: 6.9952. Min Act: -0.1700
Data Index: 2450481 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6827. Min Range: -7.6827
Max Act: 6.9640. Min Act: -0.1699
Data Index: 445577 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6827. Min Range: -7.6827
Max Act: 6.9327. Min Act: -0.1700
Data Index: 3876908 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6827. Min Range: -7.6827
Max Act: 6.9327. Min Act: -0.1700
Data Index: 1679279 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19