Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3965 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.5129. Min Act: -0.1700
Data Index: 4598854 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.4642. Min Act: -0.1697
Data Index: 5028843 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.4642. Min Act: -0.1700
Data Index: 2339492 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.4967. Min Act: -0.1700
Data Index: 6936896 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.4480. Min Act: -0.1700
Data Index: 1517016 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.4480. Min Act: -0.1700
Data Index: 4987138 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.4317. Min Act: -0.1700
Data Index: 6437417 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.4317. Min Act: -0.1700
Data Index: 190433 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.4317. Min Act: -0.1700
Data Index: 1421901 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.4317. Min Act: -0.1700
Data Index: 190424 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.3991. Min Act: -0.1699
Data Index: 190422 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.4154. Min Act: -0.1694
Data Index: 190431 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.3991. Min Act: -0.1700
Data Index: 6936881 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.4154. Min Act: -0.1700
Data Index: 7588437 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.4154. Min Act: -0.1699
Data Index: 7588434 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.3991. Min Act: -0.1700
Data Index: 2339490 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.4154. Min Act: -0.1700
Data Index: 6460369 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.4317. Min Act: -0.1699
Data Index: 3227832 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.3991. Min Act: -0.1700
Data Index: 1204028 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.3991. Min Act: -0.1700
Data Index: 3558765 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19