Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3084 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.6619. Min Act: -0.1700
Data Index: 6069987 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.5994. Min Act: -0.1700
Data Index: 169023 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.6619. Min Act: -0.1700
Data Index: 4645489 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.6306. Min Act: -0.1700
Data Index: 5988884 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.5369. Min Act: -0.1700
Data Index: 3107329 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.4744. Min Act: -0.1700
Data Index: 2861163 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.4744. Min Act: -0.1700
Data Index: 6188994 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.4744. Min Act: -0.1700
Data Index: 7032868 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.3806. Min Act: -0.1700
Data Index: 1082288 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.3181. Min Act: -0.1700
Data Index: 8824194 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.3181. Min Act: -0.1700
Data Index: 5399734 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.3181. Min Act: -0.1700
Data Index: 75372 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.2556. Min Act: -0.1700
Data Index: 541537 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.2869. Min Act: -0.1700
Data Index: 5057938 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.2556. Min Act: -0.1700
Data Index: 271801 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.2556. Min Act: -0.1700
Data Index: 5193981 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.2869. Min Act: -0.1700
Data Index: 4464998 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.2556. Min Act: -0.1700
Data Index: 2886684 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.2869. Min Act: -0.1700
Data Index: 2692813 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6619. Min Range: -7.6619
Max Act: 7.2556. Min Act: -0.1700
Data Index: 1648680 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19