Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3581 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4497. Min Range: -9.4497
Max Act: 9.4497. Min Act: -0.1700
Data Index: 7549973 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4497. Min Range: -9.4497
Max Act: 9.3247. Min Act: -0.1700
Data Index: 22479 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4497. Min Range: -9.4497
Max Act: 9.3247. Min Act: -0.1700
Data Index: 5063634 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4497. Min Range: -9.4497
Max Act: 9.2622. Min Act: -0.1700
Data Index: 5190164 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4497. Min Range: -9.4497
Max Act: 9.1997. Min Act: -0.1700
Data Index: 8041426 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4497. Min Range: -9.4497
Max Act: 9.1997. Min Act: -0.1700
Data Index: 605086 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4497. Min Range: -9.4497
Max Act: 9.1997. Min Act: -0.1700
Data Index: 7201061 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4497. Min Range: -9.4497
Max Act: 9.1372. Min Act: -0.1700
Data Index: 1865214 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4497. Min Range: -9.4497
Max Act: 8.9497. Min Act: -0.1700
Data Index: 2387880 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4497. Min Range: -9.4497
Max Act: 8.9497. Min Act: -0.1700
Data Index: 7441289 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4497. Min Range: -9.4497
Max Act: 8.9497. Min Act: -0.1700
Data Index: 4195758 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4497. Min Range: -9.4497
Max Act: 8.9497. Min Act: -0.1700
Data Index: 8735365 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4497. Min Range: -9.4497
Max Act: 8.8872. Min Act: -0.1700
Data Index: 745600 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4497. Min Range: -9.4497
Max Act: 8.8872. Min Act: -0.1700
Data Index: 2406798 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4497. Min Range: -9.4497
Max Act: 8.8872. Min Act: -0.1700
Data Index: 7582279 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4497. Min Range: -9.4497
Max Act: 8.8872. Min Act: -0.1700
Data Index: 1055774 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4497. Min Range: -9.4497
Max Act: 8.8247. Min Act: -0.1700
Data Index: 4946875 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4497. Min Range: -9.4497
Max Act: 8.7622. Min Act: -0.1700
Data Index: 137455 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4497. Min Range: -9.4497
Max Act: 8.8247. Min Act: -0.1700
Data Index: 4018683 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4497. Min Range: -9.4497
Max Act: 8.8247. Min Act: -0.1700
Data Index: 6911216 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19