Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3159 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.3460. Min Act: -0.1700
Data Index: 837328 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.3772. Min Act: -0.1700
Data Index: 4493906 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.3772. Min Act: -0.1700
Data Index: 5200497 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.3147. Min Act: -0.1700
Data Index: 7378740 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.2522. Min Act: -0.1700
Data Index: 7911334 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.2522. Min Act: -0.1700
Data Index: 6495936 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.2209. Min Act: -0.1700
Data Index: 7523493 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1897. Min Act: -0.1700
Data Index: 5857141 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1897. Min Act: -0.1700
Data Index: 1864775 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1897. Min Act: -0.1700
Data Index: 5634165 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1897. Min Act: -0.1700
Data Index: 172608 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1897. Min Act: -0.1700
Data Index: 3770980 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1897. Min Act: -0.1700
Data Index: 7922877 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1584. Min Act: -0.1700
Data Index: 2041665 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1584. Min Act: -0.1700
Data Index: 8795345 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1584. Min Act: -0.1700
Data Index: 5315692 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1584. Min Act: -0.1700
Data Index: 6451534 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1584. Min Act: -0.1700
Data Index: 6384665 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1584. Min Act: -0.1700
Data Index: 6325743 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1272. Min Act: -0.1700
Data Index: 1725762 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19