Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3387 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1489. Min Range: -5.1489
Max Act: 5.1489. Min Act: -0.1700
Data Index: 909875 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1489. Min Range: -5.1489
Max Act: 5.1177. Min Act: -0.1700
Data Index: 7405051 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1489. Min Range: -5.1489
Max Act: 5.0239. Min Act: -0.1700
Data Index: 3705126 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.7739. Min Act: -0.1700
Data Index: 7523432 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.1489. Min Act: -0.1700
Data Index: 4575764 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.1489. Min Act: -0.1700
Data Index: 4706869 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.0551. Min Act: -0.1700
Data Index: 1766837 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.0239. Min Act: -0.1700
Data Index: 3688507 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1489. Min Range: -5.1489
Max Act: 3.9926. Min Act: -0.1700
Data Index: 23683 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1489. Min Range: -5.1489
Max Act: 3.9926. Min Act: -0.1700
Data Index: 4302957 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1489. Min Range: -5.1489
Max Act: 3.9613. Min Act: -0.1700
Data Index: 445456 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1489. Min Range: -5.1489
Max Act: 3.9613. Min Act: -0.1700
Data Index: 8447240 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1489. Min Range: -5.1489
Max Act: 3.9613. Min Act: -0.1700
Data Index: 5862582 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1489. Min Range: -5.1489
Max Act: 3.9613. Min Act: -0.1700
Data Index: 5960889 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1489. Min Range: -5.1489
Max Act: 3.9613. Min Act: -0.1700
Data Index: 5875217 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1489. Min Range: -5.1489
Max Act: 3.9613. Min Act: -0.1700
Data Index: 240853 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1489. Min Range: -5.1489
Max Act: 3.9613. Min Act: -0.1700
Data Index: 730250 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1489. Min Range: -5.1489
Max Act: 3.9301. Min Act: -0.1700
Data Index: 4320150 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1489. Min Range: -5.1489
Max Act: 3.9301. Min Act: -0.1700
Data Index: 3219524 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1489. Min Range: -5.1489
Max Act: 3.9301. Min Act: -0.1700
Data Index: 4495738 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19