Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4578 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3604. Min Range: -4.3604
Max Act: 4.3604. Min Act: -0.1700
Data Index: 4763024 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3604. Min Range: -4.3604
Max Act: 4.1416. Min Act: -0.1700
Data Index: 5994597 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3604. Min Range: -4.3604
Max Act: 4.1416. Min Act: -0.1700
Data Index: 4000510 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3604. Min Range: -4.3604
Max Act: 4.0791. Min Act: -0.1700
Data Index: 6472770 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3604. Min Range: -4.3604
Max Act: 4.0791. Min Act: -0.1700
Data Index: 5579656 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3604. Min Range: -4.3604
Max Act: 4.0791. Min Act: -0.1700
Data Index: 5598360 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3604. Min Range: -4.3604
Max Act: 4.0791. Min Act: -0.1700
Data Index: 8493399 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3604. Min Range: -4.3604
Max Act: 4.0478. Min Act: -0.1700
Data Index: 5198774 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3604. Min Range: -4.3604
Max Act: 4.0478. Min Act: -0.1700
Data Index: 5512778 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3604. Min Range: -4.3604
Max Act: 4.0166. Min Act: -0.1700
Data Index: 7626146 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3604. Min Range: -4.3604
Max Act: 4.0166. Min Act: -0.1700
Data Index: 1503849 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3604. Min Range: -4.3604
Max Act: 4.0166. Min Act: -0.1700
Data Index: 201036 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3604. Min Range: -4.3604
Max Act: 4.0166. Min Act: -0.1700
Data Index: 6797519 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3604. Min Range: -4.3604
Max Act: 3.9853. Min Act: -0.1700
Data Index: 2062964 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3604. Min Range: -4.3604
Max Act: 3.9853. Min Act: -0.1700
Data Index: 31011 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3604. Min Range: -4.3604
Max Act: 3.9853. Min Act: -0.1700
Data Index: 2700812 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3604. Min Range: -4.3604
Max Act: 3.9853. Min Act: -0.1700
Data Index: 248126 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3604. Min Range: -4.3604
Max Act: 3.9853. Min Act: -0.1700
Data Index: 2127999 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3604. Min Range: -4.3604
Max Act: 3.9853. Min Act: -0.1700
Data Index: 888136 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3604. Min Range: -4.3604
Max Act: 3.9853. Min Act: -0.1700
Data Index: 2752384 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19