Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5122 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4980. Min Range: -6.4980
Max Act: 6.4980. Min Act: -0.1700
Data Index: 1145045 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4980. Min Range: -6.4980
Max Act: 6.2167. Min Act: -0.1700
Data Index: 4555742 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4980. Min Range: -6.4980
Max Act: 6.2167. Min Act: -0.1700
Data Index: 5399569 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4980. Min Range: -6.4980
Max Act: 6.1542. Min Act: -0.1700
Data Index: 251371 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4980. Min Range: -6.4980
Max Act: 6.0605. Min Act: -0.1700
Data Index: 6624797 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4980. Min Range: -6.4980
Max Act: 6.0605. Min Act: -0.1700
Data Index: 1346614 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4980. Min Range: -6.4980
Max Act: 5.9980. Min Act: -0.1700
Data Index: 7272003 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4980. Min Range: -6.4980
Max Act: 5.9980. Min Act: -0.1700
Data Index: 1007318 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4980. Min Range: -6.4980
Max Act: 5.9667. Min Act: -0.1700
Data Index: 723601 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4980. Min Range: -6.4980
Max Act: 5.9355. Min Act: -0.1700
Data Index: 5481389 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4980. Min Range: -6.4980
Max Act: 5.8730. Min Act: -0.1700
Data Index: 1314461 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4980. Min Range: -6.4980
Max Act: 5.8730. Min Act: -0.1700
Data Index: 5436173 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4980. Min Range: -6.4980
Max Act: 5.8417. Min Act: -0.1700
Data Index: 3867641 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4980. Min Range: -6.4980
Max Act: 5.8730. Min Act: -0.1700
Data Index: 5436164 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4980. Min Range: -6.4980
Max Act: 5.8417. Min Act: -0.1700
Data Index: 8378096 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4980. Min Range: -6.4980
Max Act: 5.8105. Min Act: -0.1700
Data Index: 5382650 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4980. Min Range: -6.4980
Max Act: 5.8105. Min Act: -0.1700
Data Index: 5606096 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4980. Min Range: -6.4980
Max Act: 5.8105. Min Act: -0.1700
Data Index: 6140347 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4980. Min Range: -6.4980
Max Act: 5.8105. Min Act: -0.1700
Data Index: 3070767 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4980. Min Range: -6.4980
Max Act: 5.8417. Min Act: -0.1700
Data Index: 3059070 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19