Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2938 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.7696. Min Act: -0.1700
Data Index: 1684666 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.7540. Min Act: -0.1700
Data Index: 6394011 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.6132. Min Act: -0.1700
Data Index: 5547033 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.5506. Min Act: -0.1700
Data Index: 2853634 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.5662. Min Act: -0.1700
Data Index: 5384172 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.5506. Min Act: -0.1700
Data Index: 5020845 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.5506. Min Act: -0.1700
Data Index: 2807590 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.5349. Min Act: -0.1700
Data Index: 8750081 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.5036. Min Act: -0.1700
Data Index: 7834206 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.4879. Min Act: -0.1700
Data Index: 5658231 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.4723. Min Act: -0.1700
Data Index: 8246406 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.4566. Min Act: -0.1700
Data Index: 3322904 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.4409. Min Act: -0.1700
Data Index: 8609975 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.4409. Min Act: -0.1700
Data Index: 2700828 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.4409. Min Act: -0.1700
Data Index: 5711885 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.4096. Min Act: -0.1700
Data Index: 2807584 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.4096. Min Act: -0.1700
Data Index: 5661720 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.4253. Min Act: -0.1700
Data Index: 8414938 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.4253. Min Act: -0.1700
Data Index: 3777359 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7696. Min Range: -3.7696
Max Act: 3.4096. Min Act: -0.1700
Data Index: 4399774 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19