Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1184 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2311. Min Range: -6.2311
Max Act: 6.2311. Min Act: -0.1700
Data Index: 6557659 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.9498. Min Act: -0.1700
Data Index: 4086079 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.9498. Min Act: -0.1700
Data Index: 3014837 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.9186. Min Act: -0.1700
Data Index: 1310608 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.9186. Min Act: -0.1700
Data Index: 1731321 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.8561. Min Act: -0.1700
Data Index: 1125864 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.7936. Min Act: -0.1700
Data Index: 3519833 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.7311. Min Act: -0.1700
Data Index: 2787600 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.7311. Min Act: -0.1700
Data Index: 4283450 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.7311. Min Act: -0.1700
Data Index: 2739319 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.6998. Min Act: -0.1700
Data Index: 2103428 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.6686. Min Act: -0.1700
Data Index: 7529593 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.6686. Min Act: -0.1700
Data Index: 6986118 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.6998. Min Act: -0.1700
Data Index: 3725573 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.6061. Min Act: -0.1700
Data Index: 7742737 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.6373. Min Act: -0.1700
Data Index: 5844574 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.6373. Min Act: -0.1700
Data Index: 4474612 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.6373. Min Act: -0.1700
Data Index: 8259594 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.6373. Min Act: -0.1700
Data Index: 1170628 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2311. Min Range: -6.2311
Max Act: 5.6061. Min Act: -0.1700
Data Index: 7257036 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19