Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3680 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0694. Min Range: -8.0694
Max Act: 8.0694. Min Act: -0.1700
Data Index: 2650304 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.9444. Min Act: -0.1700
Data Index: 2794461 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.6006. Min Act: -0.1700
Data Index: 3997080 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.5381. Min Act: -0.1700
Data Index: 390664 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.5069. Min Act: -0.1700
Data Index: 7718674 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.5069. Min Act: -0.1700
Data Index: 3930840 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.3506. Min Act: -0.1700
Data Index: 6434341 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.3819. Min Act: -0.1700
Data Index: 7694407 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.3194. Min Act: -0.1700
Data Index: 8546211 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.3194. Min Act: -0.1700
Data Index: 8667094 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.3194. Min Act: -0.1700
Data Index: 1944886 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.3194. Min Act: -0.1700
Data Index: 8187819 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.3194. Min Act: -0.1700
Data Index: 6181678 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.3194. Min Act: -0.1700
Data Index: 6342786 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.3194. Min Act: -0.1700
Data Index: 8726883 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.2881. Min Act: -0.1700
Data Index: 8596289 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.2569. Min Act: -0.1700
Data Index: 547909 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.2569. Min Act: -0.1700
Data Index: 2708115 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.2256. Min Act: -0.1700
Data Index: 8725610 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0694. Min Range: -8.0694
Max Act: 7.2256. Min Act: -0.1700
Data Index: 822180 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19