Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4377 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.4151. Min Act: -0.1700
Data Index: 2236691 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.2901. Min Act: -0.1700
Data Index: 5986352 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.2901. Min Act: -0.1700
Data Index: 8211480 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.2588. Min Act: -0.1700
Data Index: 8660991 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.1963. Min Act: -0.1700
Data Index: 3769753 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.1963. Min Act: -0.1700
Data Index: 1120021 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.1963. Min Act: -0.1700
Data Index: 587254 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.1651. Min Act: -0.1700
Data Index: 4131953 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.1651. Min Act: -0.1700
Data Index: 1788454 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.1651. Min Act: -0.1700
Data Index: 2325445 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.0713. Min Act: -0.1700
Data Index: 7286774 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.1026. Min Act: -0.1700
Data Index: 1934127 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.0713. Min Act: -0.1700
Data Index: 4252220 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.0401. Min Act: -0.1700
Data Index: 6096304 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.0713. Min Act: -0.1700
Data Index: 4959259 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.0713. Min Act: -0.1700
Data Index: 5337688 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.0713. Min Act: -0.1700
Data Index: 3509182 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.0713. Min Act: -0.1700
Data Index: 2103427 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.0401. Min Act: -0.1700
Data Index: 4769880 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4151. Min Range: -6.4151
Max Act: 6.0401. Min Act: -0.1700
Data Index: 4370218 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19