Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3067 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0313. Min Range: -6.0313
Max Act: 6.0313. Min Act: -0.1700
Data Index: 6606717 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0313. Min Range: -6.0313
Max Act: 6.0313. Min Act: -0.1700
Data Index: 2519946 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0313. Min Range: -6.0313
Max Act: 5.8438. Min Act: -0.1700
Data Index: 1436887 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0313. Min Range: -6.0313
Max Act: 5.8438. Min Act: -0.1700
Data Index: 940042 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0313. Min Range: -6.0313
Max Act: 5.7813. Min Act: -0.1700
Data Index: 4652486 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0313. Min Range: -6.0313
Max Act: 5.7501. Min Act: -0.1700
Data Index: 8584986 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0313. Min Range: -6.0313
Max Act: 5.7501. Min Act: -0.1700
Data Index: 893383 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0313. Min Range: -6.0313
Max Act: 5.7188. Min Act: -0.1700
Data Index: 2606019 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0313. Min Range: -6.0313
Max Act: 5.6563. Min Act: -0.1700
Data Index: 432477 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0313. Min Range: -6.0313
Max Act: 5.6563. Min Act: -0.1700
Data Index: 3308554 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0313. Min Range: -6.0313
Max Act: 5.6876. Min Act: -0.1700
Data Index: 1362508 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0313. Min Range: -6.0313
Max Act: 5.6563. Min Act: -0.1700
Data Index: 1822826 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0313. Min Range: -6.0313
Max Act: 5.6563. Min Act: -0.1700
Data Index: 3977785 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0313. Min Range: -6.0313
Max Act: 5.6563. Min Act: -0.1700
Data Index: 232985 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0313. Min Range: -6.0313
Max Act: 5.6251. Min Act: -0.1700
Data Index: 1551997 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0313. Min Range: -6.0313
Max Act: 5.6251. Min Act: -0.1700
Data Index: 8555308 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0313. Min Range: -6.0313
Max Act: 5.6251. Min Act: -0.1700
Data Index: 7096776 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0313. Min Range: -6.0313
Max Act: 5.6251. Min Act: -0.1700
Data Index: 564671 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0313. Min Range: -6.0313
Max Act: 5.5626. Min Act: -0.1700
Data Index: 6083331 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0313. Min Range: -6.0313
Max Act: 5.5938. Min Act: -0.1700
Data Index: 3475030 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19