Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2914 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6522. Min Range: -6.6522
Max Act: 6.6522. Min Act: -0.1700
Data Index: 4367172 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6522. Min Range: -6.6522
Max Act: 6.2147. Min Act: -0.1700
Data Index: 5096189 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6522. Min Range: -6.6522
Max Act: 6.2147. Min Act: -0.1700
Data Index: 8717686 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6522. Min Range: -6.6522
Max Act: 6.1835. Min Act: -0.1700
Data Index: 8491106 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6522. Min Range: -6.6522
Max Act: 6.1835. Min Act: -0.1700
Data Index: 4231859 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6522. Min Range: -6.6522
Max Act: 6.2147. Min Act: -0.1700
Data Index: 1838634 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6522. Min Range: -6.6522
Max Act: 6.1522. Min Act: -0.1700
Data Index: 6667241 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6522. Min Range: -6.6522
Max Act: 6.1522. Min Act: -0.1700
Data Index: 43 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6522. Min Range: -6.6522
Max Act: 6.1522. Min Act: -0.1700
Data Index: 6984188 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6522. Min Range: -6.6522
Max Act: 6.0897. Min Act: -0.1700
Data Index: 4219361 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6522. Min Range: -6.6522
Max Act: 6.0585. Min Act: -0.1700
Data Index: 6929188 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6522. Min Range: -6.6522
Max Act: 5.9960. Min Act: -0.1700
Data Index: 7027222 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6522. Min Range: -6.6522
Max Act: 5.9960. Min Act: -0.1700
Data Index: 1900935 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6522. Min Range: -6.6522
Max Act: 6.0272. Min Act: -0.1700
Data Index: 6011513 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6522. Min Range: -6.6522
Max Act: 5.9960. Min Act: -0.1700
Data Index: 4381114 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6522. Min Range: -6.6522
Max Act: 5.9647. Min Act: -0.1700
Data Index: 3457870 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6522. Min Range: -6.6522
Max Act: 5.9647. Min Act: -0.1700
Data Index: 5887316 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6522. Min Range: -6.6522
Max Act: 5.9647. Min Act: -0.1700
Data Index: 3829031 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6522. Min Range: -6.6522
Max Act: 5.9335. Min Act: -0.1700
Data Index: 578466 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6522. Min Range: -6.6522
Max Act: 5.9335. Min Act: -0.1700
Data Index: 5778756 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19