Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3627 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.9408. Min Act: -0.1700
Data Index: 6222228 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.8158. Min Act: -0.1700
Data Index: 1196885 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.7533. Min Act: -0.1700
Data Index: 3319248 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.7845. Min Act: -0.1700
Data Index: 7345993 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.7845. Min Act: -0.1700
Data Index: 1925668 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.7220. Min Act: -0.1700
Data Index: 4312543 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.7220. Min Act: -0.1700
Data Index: 6934620 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.7533. Min Act: -0.1700
Data Index: 6772950 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.7220. Min Act: -0.1700
Data Index: 4382506 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.7220. Min Act: -0.1700
Data Index: 4231325 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.6908. Min Act: -0.1700
Data Index: 1206588 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.6283. Min Act: -0.1700
Data Index: 2725054 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.6283. Min Act: -0.1700
Data Index: 4498467 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.6283. Min Act: -0.1700
Data Index: 7570332 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.6283. Min Act: -0.1700
Data Index: 6292414 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.5970. Min Act: -0.1700
Data Index: 5429197 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.5658. Min Act: -0.1700
Data Index: 5962463 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.5658. Min Act: -0.1700
Data Index: 8499885 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.5658. Min Act: -0.1700
Data Index: 6785977 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9408. Min Range: -6.9408
Max Act: 6.5658. Min Act: -0.1700
Data Index: 6260946 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19