Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4098 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.5281. Min Act: -0.1700
Data Index: 6946417 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.4656. Min Act: -0.1700
Data Index: 6606159 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.4343. Min Act: -0.1700
Data Index: 2683991 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.4343. Min Act: -0.1700
Data Index: 4371998 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.4343. Min Act: -0.1700
Data Index: 8320380 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.3718. Min Act: -0.1700
Data Index: 1398177 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.4031. Min Act: -0.1700
Data Index: 6334880 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.3406. Min Act: -0.1700
Data Index: 2233574 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.3093. Min Act: -0.1700
Data Index: 2621935 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.3093. Min Act: -0.1700
Data Index: 6774601 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.3093. Min Act: -0.1700
Data Index: 5931127 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.3406. Min Act: -0.1700
Data Index: 2396041 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.2781. Min Act: -0.1700
Data Index: 7322991 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.2781. Min Act: -0.1700
Data Index: 2288961 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.3093. Min Act: -0.1700
Data Index: 4462577 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.2468. Min Act: -0.1700
Data Index: 2303642 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.2156. Min Act: -0.1700
Data Index: 7197296 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.1843. Min Act: -0.1700
Data Index: 8805105 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.2156. Min Act: -0.1700
Data Index: 6741406 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5281. Min Range: -6.5281
Max Act: 6.1843. Min Act: -0.1700
Data Index: 2186451 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19