Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5295 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1700. Min Range: -6.1700
Max Act: 6.1700. Min Act: -0.1700
Data Index: 654190 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1700. Min Range: -6.1700
Max Act: 6.1700. Min Act: -0.1700
Data Index: 1794844 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1700. Min Range: -6.1700
Max Act: 6.0450. Min Act: -0.1700
Data Index: 1355064 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1700. Min Range: -6.1700
Max Act: 6.0450. Min Act: -0.1700
Data Index: 3116611 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1700. Min Range: -6.1700
Max Act: 5.9512. Min Act: -0.1700
Data Index: 6206078 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1700. Min Range: -6.1700
Max Act: 5.9200. Min Act: -0.1700
Data Index: 2520806 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1700. Min Range: -6.1700
Max Act: 5.9200. Min Act: -0.1700
Data Index: 2115956 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1700. Min Range: -6.1700
Max Act: 5.9200. Min Act: -0.1700
Data Index: 3453871 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1700. Min Range: -6.1700
Max Act: 5.8887. Min Act: -0.1700
Data Index: 5933185 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1700. Min Range: -6.1700
Max Act: 5.8575. Min Act: -0.1700
Data Index: 5435408 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1700. Min Range: -6.1700
Max Act: 5.8575. Min Act: -0.1700
Data Index: 8553045 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1700. Min Range: -6.1700
Max Act: 5.8575. Min Act: -0.1700
Data Index: 5431845 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1700. Min Range: -6.1700
Max Act: 5.8262. Min Act: -0.1700
Data Index: 4890855 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1700. Min Range: -6.1700
Max Act: 5.8262. Min Act: -0.1700
Data Index: 3026523 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1700. Min Range: -6.1700
Max Act: 5.7637. Min Act: -0.1700
Data Index: 4142321 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1700. Min Range: -6.1700
Max Act: 5.7950. Min Act: -0.1700
Data Index: 5290367 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1700. Min Range: -6.1700
Max Act: 5.7950. Min Act: -0.1700
Data Index: 8170246 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1700. Min Range: -6.1700
Max Act: 5.7637. Min Act: -0.1700
Data Index: 6917719 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1700. Min Range: -6.1700
Max Act: 5.7637. Min Act: -0.1700
Data Index: 2084717 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1700. Min Range: -6.1700
Max Act: 5.7637. Min Act: -0.1700
Data Index: 3000125 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19