Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5833 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4788. Min Range: -4.4788
Max Act: 4.4788. Min Act: -0.1700
Data Index: 6503285 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4788. Min Range: -4.4788
Max Act: 4.1975. Min Act: -0.1695
Data Index: 7087258 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4788. Min Range: -4.4788
Max Act: 4.1663. Min Act: -0.1700
Data Index: 6503283 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4788. Min Range: -4.4788
Max Act: 4.1350. Min Act: -0.1700
Data Index: 7087252 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4788. Min Range: -4.4788
Max Act: 4.1038. Min Act: -0.1700
Data Index: 7087259 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4788. Min Range: -4.4788
Max Act: 4.0412. Min Act: -0.1700
Data Index: 7087257 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4788. Min Range: -4.4788
Max Act: 4.0100. Min Act: -0.1700
Data Index: 7087253 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4788. Min Range: -4.4788
Max Act: 4.0100. Min Act: -0.1700
Data Index: 7087256 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4788. Min Range: -4.4788
Max Act: 3.9787. Min Act: -0.1700
Data Index: 7087255 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4788. Min Range: -4.4788
Max Act: 3.9475. Min Act: -0.1700
Data Index: 5474819 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4788. Min Range: -4.4788
Max Act: 3.9162. Min Act: -0.1699
Data Index: 42921 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4788. Min Range: -4.4788
Max Act: 3.9162. Min Act: -0.1700
Data Index: 7087254 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4788. Min Range: -4.4788
Max Act: 3.7911. Min Act: -0.1700
Data Index: 1240240 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4788. Min Range: -4.4788
Max Act: 3.7598. Min Act: -0.1700
Data Index: 6503284 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4788. Min Range: -4.4788
Max Act: 3.7286. Min Act: -0.1700
Data Index: 6525099 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4788. Min Range: -4.4788
Max Act: 3.7286. Min Act: -0.1700
Data Index: 6925160 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4788. Min Range: -4.4788
Max Act: 3.7286. Min Act: -0.1700
Data Index: 3367455 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4788. Min Range: -4.4788
Max Act: 3.6973. Min Act: -0.1699
Data Index: 983540 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4788. Min Range: -4.4788
Max Act: 3.6660. Min Act: -0.1700
Data Index: 6525106 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4788. Min Range: -4.4788
Max Act: 3.6660. Min Act: -0.1700
Data Index: 4354029 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19