Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3468 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3049. Min Range: -8.3049
Max Act: 8.3049. Min Act: -0.1700
Data Index: 4998153 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3049. Min Range: -8.3049
Max Act: 8.1174. Min Act: -0.1700
Data Index: 1313641 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3049. Min Range: -8.3049
Max Act: 8.1174. Min Act: -0.1700
Data Index: 4660658 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3049. Min Range: -8.3049
Max Act: 7.9924. Min Act: -0.1700
Data Index: 2687506 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3049. Min Range: -8.3049
Max Act: 7.9299. Min Act: -0.1700
Data Index: 5768533 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3049. Min Range: -8.3049
Max Act: 7.9612. Min Act: -0.1700
Data Index: 4767519 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3049. Min Range: -8.3049
Max Act: 7.8987. Min Act: -0.1700
Data Index: 1524980 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3049. Min Range: -8.3049
Max Act: 7.8674. Min Act: -0.1700
Data Index: 8702460 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3049. Min Range: -8.3049
Max Act: 7.8674. Min Act: -0.1700
Data Index: 5523839 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3049. Min Range: -8.3049
Max Act: 7.8674. Min Act: -0.1700
Data Index: 3080623 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3049. Min Range: -8.3049
Max Act: 7.8362. Min Act: -0.1700
Data Index: 3452262 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3049. Min Range: -8.3049
Max Act: 7.8049. Min Act: -0.1700
Data Index: 3848275 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3049. Min Range: -8.3049
Max Act: 7.8362. Min Act: -0.1700
Data Index: 4459024 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3049. Min Range: -8.3049
Max Act: 7.7424. Min Act: -0.1700
Data Index: 5055097 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3049. Min Range: -8.3049
Max Act: 7.7112. Min Act: -0.1700
Data Index: 5611167 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3049. Min Range: -8.3049
Max Act: 7.7112. Min Act: -0.1700
Data Index: 4932025 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3049. Min Range: -8.3049
Max Act: 7.6799. Min Act: -0.1700
Data Index: 7108555 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3049. Min Range: -8.3049
Max Act: 7.7112. Min Act: -0.1700
Data Index: 582894 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3049. Min Range: -8.3049
Max Act: 7.6799. Min Act: -0.1700
Data Index: 5468591 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3049. Min Range: -8.3049
Max Act: 7.6487. Min Act: -0.1700
Data Index: 5614966 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19