Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2945 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.6453. Min Act: -0.1700
Data Index: 6335079 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.4890. Min Act: -0.1700
Data Index: 5700888 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.5203. Min Act: -0.1700
Data Index: 1082878 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.4890. Min Act: -0.1700
Data Index: 652042 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.4578. Min Act: -0.1700
Data Index: 1431505 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.4578. Min Act: -0.1700
Data Index: 8269098 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.3953. Min Act: -0.1700
Data Index: 3216415 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.3015. Min Act: -0.1700
Data Index: 7560718 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.3328. Min Act: -0.1700
Data Index: 4565415 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.3015. Min Act: -0.1700
Data Index: 2177595 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.3015. Min Act: -0.1700
Data Index: 7116081 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.2703. Min Act: -0.1700
Data Index: 4046550 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.2703. Min Act: -0.1700
Data Index: 4227600 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.2703. Min Act: -0.1700
Data Index: 2829916 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.2703. Min Act: -0.1700
Data Index: 4745667 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.2390. Min Act: -0.1700
Data Index: 4226797 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.2390. Min Act: -0.1700
Data Index: 1841943 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.1765. Min Act: -0.1700
Data Index: 3995881 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.1765. Min Act: -0.1700
Data Index: 8472352 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6453. Min Range: -7.6453
Max Act: 7.1453. Min Act: -0.1700
Data Index: 125901 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19