Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4586 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1060. Min Range: -3.1060
Max Act: 3.1060. Min Act: -0.1700
Data Index: 3689466 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8370. Min Act: -0.1700
Data Index: 6002164 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8370. Min Act: -0.1700
Data Index: 1650938 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8052. Min Act: -0.1700
Data Index: 7009073 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.7893. Min Act: -0.1700
Data Index: 2233830 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.7893. Min Act: -0.1700
Data Index: 652314 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.7734. Min Act: -0.1700
Data Index: 8669059 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.7574. Min Act: -0.1700
Data Index: 4285601 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.7414. Min Act: -0.1700
Data Index: 3501368 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.7255. Min Act: -0.1700
Data Index: 94122 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.7255. Min Act: -0.1700
Data Index: 1014521 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.6935. Min Act: -0.1700
Data Index: 3535163 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.7095. Min Act: -0.1700
Data Index: 4078664 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.6935. Min Act: -0.1700
Data Index: 5859245 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.6775. Min Act: -0.1700
Data Index: 3535162 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.6775. Min Act: -0.1700
Data Index: 6131231 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.6614. Min Act: -0.1700
Data Index: 1196932 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.6614. Min Act: -0.1700
Data Index: 3409917 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.6614. Min Act: -0.1700
Data Index: 3425992 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.6614. Min Act: -0.1700
Data Index: 4587347 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19