Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3170 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.7950. Min Act: -0.1700
Data Index: 6612479 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.7638. Min Act: -0.1700
Data Index: 7780242 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.7013. Min Act: -0.1700
Data Index: 1178494 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.6388. Min Act: -0.1700
Data Index: 3332220 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.6075. Min Act: -0.1700
Data Index: 2905033 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.6075. Min Act: -0.1700
Data Index: 5707577 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.5138. Min Act: -0.1700
Data Index: 3837699 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.5138. Min Act: -0.1700
Data Index: 952655 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.5138. Min Act: -0.1700
Data Index: 1415400 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.5138. Min Act: -0.1700
Data Index: 4650139 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.5138. Min Act: -0.1700
Data Index: 4092447 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.4825. Min Act: -0.1700
Data Index: 4094623 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.4513. Min Act: -0.1700
Data Index: 1204591 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.4513. Min Act: -0.1700
Data Index: 6087959 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.4513. Min Act: -0.1700
Data Index: 6076809 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.4513. Min Act: -0.1700
Data Index: 4862159 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.4200. Min Act: -0.1700
Data Index: 5214248 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.4200. Min Act: -0.1700
Data Index: 2045989 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.4200. Min Act: -0.1700
Data Index: 1029867 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7950. Min Range: -6.7950
Max Act: 6.4200. Min Act: -0.1700
Data Index: 824736 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19