Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3257 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1763. Min Range: -7.1763
Max Act: 7.1763. Min Act: -0.1700
Data Index: 1320483 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.9576. Min Act: -0.1700
Data Index: 3300794 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.9576. Min Act: -0.1700
Data Index: 3104607 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.8951. Min Act: -0.1700
Data Index: 2983911 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.8951. Min Act: -0.1700
Data Index: 6883355 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.8013. Min Act: -0.1700
Data Index: 3225889 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.7076. Min Act: -0.1700
Data Index: 8094422 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.7388. Min Act: -0.1699
Data Index: 6899853 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.7076. Min Act: -0.1700
Data Index: 7992053 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.7076. Min Act: -0.1700
Data Index: 151577 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.6763. Min Act: -0.1700
Data Index: 469224 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.6451. Min Act: -0.1700
Data Index: 8230400 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.6451. Min Act: -0.1700
Data Index: 3600933 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.6451. Min Act: -0.1700
Data Index: 4825165 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.6451. Min Act: -0.1700
Data Index: 1100247 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.6138. Min Act: -0.1700
Data Index: 5125305 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.6451. Min Act: -0.1700
Data Index: 1078000 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.6138. Min Act: -0.1700
Data Index: 695677 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.6138. Min Act: -0.1700
Data Index: 6996396 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1763. Min Range: -7.1763
Max Act: 6.5826. Min Act: -0.1700
Data Index: 4936170 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19