Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4154 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.7688. Min Act: -0.1700
Data Index: 7124996 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.7375. Min Act: -0.1700
Data Index: 2179218 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.7063. Min Act: -0.1700
Data Index: 6203149 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.7375. Min Act: -0.1700
Data Index: 160932 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.7375. Min Act: -0.1700
Data Index: 322638 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.6438. Min Act: -0.1700
Data Index: 4939797 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.6438. Min Act: -0.1700
Data Index: 4847730 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.6750. Min Act: -0.1700
Data Index: 1927353 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.6438. Min Act: -0.1700
Data Index: 3823909 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.6438. Min Act: -0.1700
Data Index: 4873758 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.6750. Min Act: -0.1700
Data Index: 2478655 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.6125. Min Act: -0.1700
Data Index: 3608490 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.6125. Min Act: -0.1700
Data Index: 111166 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.6125. Min Act: -0.1700
Data Index: 1301887 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.6125. Min Act: -0.1700
Data Index: 4450629 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.5813. Min Act: -0.1700
Data Index: 6600154 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.5813. Min Act: -0.1700
Data Index: 8507697 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.5813. Min Act: -0.1700
Data Index: 13233 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.5813. Min Act: -0.1700
Data Index: 5179592 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7688. Min Range: -6.7688
Max Act: 6.5813. Min Act: -0.1700
Data Index: 3129570 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19