Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2581 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.7255. Min Act: -0.1700
Data Index: 4183849 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.7255. Min Act: -0.1700
Data Index: 2679745 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.6317. Min Act: -0.1700
Data Index: 5909899 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.6005. Min Act: -0.1700
Data Index: 5250759 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.5692. Min Act: -0.1700
Data Index: 4835743 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.5692. Min Act: -0.1700
Data Index: 359657 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.5067. Min Act: -0.1700
Data Index: 7564445 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.5067. Min Act: -0.1700
Data Index: 6641123 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.5067. Min Act: -0.1700
Data Index: 2555610 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.5067. Min Act: -0.1700
Data Index: 8767619 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.4755. Min Act: -0.1700
Data Index: 1829806 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.4130. Min Act: -0.1700
Data Index: 7747257 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.4130. Min Act: -0.1700
Data Index: 3652095 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.3817. Min Act: -0.1700
Data Index: 7674520 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.4130. Min Act: -0.1700
Data Index: 4418086 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.3817. Min Act: -0.1700
Data Index: 1887320 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.3817. Min Act: -0.1700
Data Index: 2838261 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.3505. Min Act: -0.1700
Data Index: 5430968 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.3817. Min Act: -0.1700
Data Index: 1623439 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7255. Min Range: -7.7255
Max Act: 7.3505. Min Act: -0.1700
Data Index: 2211832 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19