Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 582 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.8858. Min Act: -0.1700
Data Index: 1221289 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.6358. Min Act: -0.1700
Data Index: 5553721 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.5420. Min Act: -0.1700
Data Index: 3413155 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.3545. Min Act: -0.1700
Data Index: 4873475 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.3545. Min Act: -0.1700
Data Index: 3877898 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.2920. Min Act: -0.1700
Data Index: 3783013 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.2920. Min Act: -0.1700
Data Index: 4873477 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.2608. Min Act: -0.1700
Data Index: 6412570 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.2608. Min Act: -0.1700
Data Index: 2418689 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.2608. Min Act: -0.1700
Data Index: 7135348 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.2295. Min Act: -0.1700
Data Index: 6779029 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.2295. Min Act: -0.1700
Data Index: 3692416 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.2295. Min Act: -0.1700
Data Index: 2872553 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.2295. Min Act: -0.1700
Data Index: 2821941 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.1983. Min Act: -0.1700
Data Index: 1843293 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.1983. Min Act: -0.1700
Data Index: 5502280 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.1983. Min Act: -0.1700
Data Index: 8258960 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.1670. Min Act: -0.1700
Data Index: 7014008 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.1983. Min Act: -0.1700
Data Index: 5699748 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8858. Min Range: -7.8858
Max Act: 7.1358. Min Act: -0.1700
Data Index: 3872623 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19