Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1285 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.4575. Min Act: -0.1700
Data Index: 2601690 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.3950. Min Act: -0.1700
Data Index: 625280 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.4263. Min Act: -0.1700
Data Index: 524820 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.3950. Min Act: -0.1700
Data Index: 8455431 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.3950. Min Act: -0.1700
Data Index: 8761302 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.3950. Min Act: -0.1700
Data Index: 3929321 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.3638. Min Act: -0.1700
Data Index: 5303336 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.3638. Min Act: -0.1700
Data Index: 5828473 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.3325. Min Act: -0.1700
Data Index: 6149517 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.3013. Min Act: -0.1700
Data Index: 2759857 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.2388. Min Act: -0.1700
Data Index: 2992321 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.2700. Min Act: -0.1700
Data Index: 1943684 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.2700. Min Act: -0.1700
Data Index: 7141634 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.2700. Min Act: -0.1700
Data Index: 4519467 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.2388. Min Act: -0.1700
Data Index: 4057107 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.2388. Min Act: -0.1700
Data Index: 6505047 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.2388. Min Act: -0.1700
Data Index: 7506600 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.2075. Min Act: -0.1700
Data Index: 5494569 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.2075. Min Act: -0.1700
Data Index: 100414 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4575. Min Range: -6.4575
Max Act: 6.2075. Min Act: -0.1700
Data Index: 4779975 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19