Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2217. Min Range: -6.2217
Max Act: 6.2217. Min Act: -0.1700
Data Index: 885205 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2217. Min Range: -6.2217
Max Act: 6.1905. Min Act: -0.1700
Data Index: 5167353 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2217. Min Range: -6.2217
Max Act: 6.1280. Min Act: -0.1700
Data Index: 8287758 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2217. Min Range: -6.2217
Max Act: 6.1280. Min Act: -0.1700
Data Index: 4292014 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2217. Min Range: -6.2217
Max Act: 6.1280. Min Act: -0.1700
Data Index: 3922150 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2217. Min Range: -6.2217
Max Act: 6.0967. Min Act: -0.1700
Data Index: 1864981 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2217. Min Range: -6.2217
Max Act: 6.0967. Min Act: -0.1700
Data Index: 5354790 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2217. Min Range: -6.2217
Max Act: 6.0655. Min Act: -0.1700
Data Index: 6534154 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2217. Min Range: -6.2217
Max Act: 6.0030. Min Act: -0.1700
Data Index: 4730066 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2217. Min Range: -6.2217
Max Act: 5.9717. Min Act: -0.1700
Data Index: 1579138 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2217. Min Range: -6.2217
Max Act: 5.9717. Min Act: -0.1700
Data Index: 2294524 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2217. Min Range: -6.2217
Max Act: 5.9092. Min Act: -0.1700
Data Index: 6319706 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2217. Min Range: -6.2217
Max Act: 5.9092. Min Act: -0.1700
Data Index: 175016 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2217. Min Range: -6.2217
Max Act: 5.8780. Min Act: -0.1700
Data Index: 5244094 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2217. Min Range: -6.2217
Max Act: 5.8780. Min Act: -0.1700
Data Index: 3574602 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2217. Min Range: -6.2217
Max Act: 5.8780. Min Act: -0.1700
Data Index: 4978967 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2217. Min Range: -6.2217
Max Act: 5.8467. Min Act: -0.1700
Data Index: 4490028 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2217. Min Range: -6.2217
Max Act: 5.8467. Min Act: -0.1700
Data Index: 2591 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2217. Min Range: -6.2217
Max Act: 5.8155. Min Act: -0.1700
Data Index: 334894 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2217. Min Range: -6.2217
Max Act: 5.8155. Min Act: -0.1700
Data Index: 8120826 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19