Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3203 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6172. Min Range: -7.6172
Max Act: 7.6172. Min Act: -0.1700
Data Index: 1444862 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6172. Min Range: -7.6172
Max Act: 7.5547. Min Act: -0.1700
Data Index: 3991792 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6172. Min Range: -7.6172
Max Act: 7.2422. Min Act: -0.1700
Data Index: 7431061 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6172. Min Range: -7.6172
Max Act: 7.2109. Min Act: -0.1700
Data Index: 7007756 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6172. Min Range: -7.6172
Max Act: 7.1484. Min Act: -0.1700
Data Index: 2432653 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6172. Min Range: -7.6172
Max Act: 7.1172. Min Act: -0.1700
Data Index: 4439191 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6172. Min Range: -7.6172
Max Act: 7.0859. Min Act: -0.1700
Data Index: 5558252 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6172. Min Range: -7.6172
Max Act: 7.0859. Min Act: -0.1700
Data Index: 7552628 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6172. Min Range: -7.6172
Max Act: 6.9922. Min Act: -0.1700
Data Index: 7904653 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6172. Min Range: -7.6172
Max Act: 7.0234. Min Act: -0.1700
Data Index: 6237224 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6172. Min Range: -7.6172
Max Act: 6.9922. Min Act: -0.1700
Data Index: 5089129 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6172. Min Range: -7.6172
Max Act: 6.9922. Min Act: -0.1700
Data Index: 7745939 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6172. Min Range: -7.6172
Max Act: 6.9922. Min Act: -0.1700
Data Index: 490459 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6172. Min Range: -7.6172
Max Act: 6.9922. Min Act: -0.1700
Data Index: 8326363 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6172. Min Range: -7.6172
Max Act: 6.9609. Min Act: -0.1700
Data Index: 2211221 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6172. Min Range: -7.6172
Max Act: 6.9609. Min Act: -0.1700
Data Index: 4508748 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6172. Min Range: -7.6172
Max Act: 6.9297. Min Act: -0.1700
Data Index: 6095115 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6172. Min Range: -7.6172
Max Act: 6.8984. Min Act: -0.1700
Data Index: 7662370 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6172. Min Range: -7.6172
Max Act: 6.8984. Min Act: -0.1700
Data Index: 7470865 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6172. Min Range: -7.6172
Max Act: 6.8984. Min Act: -0.1700
Data Index: 5200636 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19