Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1771 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.4862. Min Act: -0.1700
Data Index: 2434968 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.3612. Min Act: -0.1700
Data Index: 2796415 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.3299. Min Act: -0.1700
Data Index: 4151156 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.2049. Min Act: -0.1700
Data Index: 5896487 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.2049. Min Act: -0.1700
Data Index: 2600526 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.2049. Min Act: -0.1700
Data Index: 5914101 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.1737. Min Act: -0.1700
Data Index: 1771940 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.1737. Min Act: -0.1700
Data Index: 6712240 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.1737. Min Act: -0.1700
Data Index: 5483641 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.1737. Min Act: -0.1700
Data Index: 1579918 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.1424. Min Act: -0.1700
Data Index: 2573569 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.1424. Min Act: -0.1700
Data Index: 1893880 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.1424. Min Act: -0.1700
Data Index: 7719892 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.1424. Min Act: -0.1700
Data Index: 8719673 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.0799. Min Act: -0.1700
Data Index: 590645 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.1112. Min Act: -0.1700
Data Index: 5596195 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.1112. Min Act: -0.1700
Data Index: 6963115 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.1424. Min Act: -0.1700
Data Index: 6393126 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.1112. Min Act: -0.1700
Data Index: 2875839 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4862. Min Range: -6.4862
Max Act: 6.1112. Min Act: -0.1700
Data Index: 2086251 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19