Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3325 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.6396. Min Act: -0.1700
Data Index: 4977963 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.5771. Min Act: -0.1700
Data Index: 1272201 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.5458. Min Act: -0.1700
Data Index: 4771921 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.5458. Min Act: -0.1700
Data Index: 5378669 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.4833. Min Act: -0.1700
Data Index: 5420942 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.4833. Min Act: -0.1700
Data Index: 1883915 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.4833. Min Act: -0.1700
Data Index: 2599015 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.4521. Min Act: -0.1700
Data Index: 1022297 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.4833. Min Act: -0.1700
Data Index: 3655565 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.4833. Min Act: -0.1700
Data Index: 818550 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.4833. Min Act: -0.1700
Data Index: 7881098 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.4833. Min Act: -0.1700
Data Index: 6465113 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.4521. Min Act: -0.1700
Data Index: 6910382 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.4521. Min Act: -0.1700
Data Index: 368194 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.4521. Min Act: -0.1700
Data Index: 7046719 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.4208. Min Act: -0.1700
Data Index: 1650319 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.3896. Min Act: -0.1700
Data Index: 1392540 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.4208. Min Act: -0.1700
Data Index: 5148831 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.4208. Min Act: -0.1700
Data Index: 2689948 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6396. Min Range: -4.6396
Max Act: 4.4208. Min Act: -0.1700
Data Index: 3576670 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19