Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1819 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.8911. Min Act: -0.1700
Data Index: 1476306 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.7036. Min Act: -0.1700
Data Index: 4315834 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.6723. Min Act: -0.1700
Data Index: 748699 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.4848. Min Act: -0.1700
Data Index: 3706557 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.3598. Min Act: -0.1700
Data Index: 6915705 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.2973. Min Act: -0.1700
Data Index: 6623954 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.2973. Min Act: -0.1700
Data Index: 2846431 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.2348. Min Act: -0.1700
Data Index: 7456347 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.2348. Min Act: -0.1700
Data Index: 6748714 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.1723. Min Act: -0.1700
Data Index: 8290278 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.1723. Min Act: -0.1700
Data Index: 690651 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.1723. Min Act: -0.1700
Data Index: 4241279 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.1411. Min Act: -0.1700
Data Index: 8790115 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.1411. Min Act: -0.1700
Data Index: 8657864 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.1098. Min Act: -0.1700
Data Index: 8065459 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.1098. Min Act: -0.1700
Data Index: 3135216 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.0786. Min Act: -0.1700
Data Index: 7229628 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.0786. Min Act: -0.1700
Data Index: 5347641 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.0786. Min Act: -0.1700
Data Index: 4002414 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.0786. Min Act: -0.1700
Data Index: 1874928 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19