Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2675 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.9149. Min Act: -0.1700
Data Index: 841901 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.8524. Min Act: -0.1700
Data Index: 8049730 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.7899. Min Act: -0.1700
Data Index: 5801810 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.7274. Min Act: -0.1700
Data Index: 5422531 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.7274. Min Act: -0.1700
Data Index: 3689375 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.6649. Min Act: -0.1700
Data Index: 4217286 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.6024. Min Act: -0.1700
Data Index: 452422 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.5399. Min Act: -0.1700
Data Index: 8381697 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.6024. Min Act: -0.1700
Data Index: 1205056 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.5399. Min Act: -0.1700
Data Index: 537028 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.6024. Min Act: -0.1700
Data Index: 5460208 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.4774. Min Act: -0.1700
Data Index: 6828783 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.4774. Min Act: -0.1700
Data Index: 4596609 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.4774. Min Act: -0.1700
Data Index: 185338 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.4774. Min Act: -0.1700
Data Index: 1618022 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.4149. Min Act: -0.1700
Data Index: 2904978 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.4149. Min Act: -0.1700
Data Index: 7153747 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.4149. Min Act: -0.1700
Data Index: 5576755 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.4149. Min Act: -0.1700
Data Index: 1606148 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9149. Min Range: -8.9149
Max Act: 8.4149. Min Act: -0.1700
Data Index: 1672742 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19