Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.8550. Min Act: -0.1700
Data Index: 4680086 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.7300. Min Act: -0.1700
Data Index: 8373516 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.6050. Min Act: -0.1700
Data Index: 1489001 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.4800. Min Act: -0.1700
Data Index: 5112416 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.4800. Min Act: -0.1700
Data Index: 2995745 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.4175. Min Act: -0.1700
Data Index: 5335189 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.3550. Min Act: -0.1700
Data Index: 5120959 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.4175. Min Act: -0.1700
Data Index: 8221393 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.3550. Min Act: -0.1700
Data Index: 6356981 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.2925. Min Act: -0.1700
Data Index: 1632448 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.2925. Min Act: -0.1700
Data Index: 6476006 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.2300. Min Act: -0.1699
Data Index: 5950320 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.2300. Min Act: -0.1700
Data Index: 3589942 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.2300. Min Act: -0.1700
Data Index: 3594666 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.2925. Min Act: -0.1700
Data Index: 6525236 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.2300. Min Act: -0.1700
Data Index: 6645913 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.2300. Min Act: -0.1697
Data Index: 135437 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.1050. Min Act: -0.1700
Data Index: 5116573 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.1675. Min Act: -0.1700
Data Index: 3913101 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8550. Min Range: -11.8550
Max Act: 11.1675. Min Act: -0.1700
Data Index: 553061 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19