Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 845 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1124. Min Range: -6.1124
Max Act: 6.1124. Min Act: -0.1700
Data Index: 1913791 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1124. Min Range: -6.1124
Max Act: 6.0499. Min Act: -0.1700
Data Index: 79069 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.9874. Min Act: -0.1700
Data Index: 79070 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.9249. Min Act: -0.1700
Data Index: 7174544 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.9562. Min Act: -0.1700
Data Index: 2716035 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.9562. Min Act: -0.1700
Data Index: 6652179 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.9249. Min Act: -0.1700
Data Index: 8199830 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.8937. Min Act: -0.1700
Data Index: 4405437 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.8624. Min Act: -0.1700
Data Index: 4964061 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.8624. Min Act: -0.1700
Data Index: 5671796 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.8312. Min Act: -0.1700
Data Index: 787149 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.8312. Min Act: -0.1700
Data Index: 783913 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.8312. Min Act: -0.1700
Data Index: 7824826 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.7999. Min Act: -0.1700
Data Index: 5056883 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.7999. Min Act: -0.1700
Data Index: 5918499 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.7999. Min Act: -0.1700
Data Index: 8732810 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.7687. Min Act: -0.1700
Data Index: 1042791 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.7999. Min Act: -0.1700
Data Index: 3704387 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.7687. Min Act: -0.1700
Data Index: 7563258 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.7687. Min Act: -0.1700
Data Index: 606513 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19