Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5554 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3424. Min Range: -6.3424
Max Act: 6.3424. Min Act: -0.1700
Data Index: 547801 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3424. Min Range: -6.3424
Max Act: 6.1862. Min Act: -0.1700
Data Index: 4722368 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3424. Min Range: -6.3424
Max Act: 6.1237. Min Act: -0.1700
Data Index: 8020576 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3424. Min Range: -6.3424
Max Act: 5.9674. Min Act: -0.1700
Data Index: 2240478 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3424. Min Range: -6.3424
Max Act: 5.9674. Min Act: -0.1700
Data Index: 1739433 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3424. Min Range: -6.3424
Max Act: 5.9362. Min Act: -0.1700
Data Index: 6484666 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3424. Min Range: -6.3424
Max Act: 5.9362. Min Act: -0.1700
Data Index: 3906518 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3424. Min Range: -6.3424
Max Act: 5.8424. Min Act: -0.1700
Data Index: 968333 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3424. Min Range: -6.3424
Max Act: 5.8424. Min Act: -0.1700
Data Index: 5165273 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3424. Min Range: -6.3424
Max Act: 5.8424. Min Act: -0.1700
Data Index: 5212025 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3424. Min Range: -6.3424
Max Act: 5.7799. Min Act: -0.1700
Data Index: 7933578 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3424. Min Range: -6.3424
Max Act: 5.7799. Min Act: -0.1700
Data Index: 3359258 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3424. Min Range: -6.3424
Max Act: 5.7487. Min Act: -0.1700
Data Index: 6250150 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3424. Min Range: -6.3424
Max Act: 5.7174. Min Act: -0.1700
Data Index: 7916705 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3424. Min Range: -6.3424
Max Act: 5.7487. Min Act: -0.1700
Data Index: 2826683 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3424. Min Range: -6.3424
Max Act: 5.6862. Min Act: -0.1700
Data Index: 6397693 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3424. Min Range: -6.3424
Max Act: 5.6862. Min Act: -0.1700
Data Index: 2259198 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3424. Min Range: -6.3424
Max Act: 5.6862. Min Act: -0.1700
Data Index: 5027951 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3424. Min Range: -6.3424
Max Act: 5.6862. Min Act: -0.1700
Data Index: 7364472 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3424. Min Range: -6.3424
Max Act: 5.6862. Min Act: -0.1700
Data Index: 5973871 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19