Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4776 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3076. Min Range: -7.3076
Max Act: 7.3076. Min Act: -0.1700
Data Index: 1391102 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3076. Min Range: -7.3076
Max Act: 7.2764. Min Act: -0.1700
Data Index: 1641823 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3076. Min Range: -7.3076
Max Act: 7.1826. Min Act: -0.1700
Data Index: 4970497 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3076. Min Range: -7.3076
Max Act: 7.0889. Min Act: -0.1700
Data Index: 348556 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3076. Min Range: -7.3076
Max Act: 7.0576. Min Act: -0.1700
Data Index: 412757 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3076. Min Range: -7.3076
Max Act: 7.0264. Min Act: -0.1700
Data Index: 446112 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3076. Min Range: -7.3076
Max Act: 6.9014. Min Act: -0.1700
Data Index: 5052804 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3076. Min Range: -7.3076
Max Act: 6.9014. Min Act: -0.1700
Data Index: 3024243 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3076. Min Range: -7.3076
Max Act: 6.9014. Min Act: -0.1700
Data Index: 3560357 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3076. Min Range: -7.3076
Max Act: 6.8701. Min Act: -0.1700
Data Index: 7334270 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3076. Min Range: -7.3076
Max Act: 6.8389. Min Act: -0.1700
Data Index: 4604779 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3076. Min Range: -7.3076
Max Act: 6.7764. Min Act: -0.1700
Data Index: 2612135 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3076. Min Range: -7.3076
Max Act: 6.7764. Min Act: -0.1700
Data Index: 3560102 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3076. Min Range: -7.3076
Max Act: 6.7764. Min Act: -0.1700
Data Index: 6797801 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3076. Min Range: -7.3076
Max Act: 6.7764. Min Act: -0.1700
Data Index: 6762250 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3076. Min Range: -7.3076
Max Act: 6.7451. Min Act: -0.1700
Data Index: 607155 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3076. Min Range: -7.3076
Max Act: 6.7451. Min Act: -0.1700
Data Index: 2167274 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3076. Min Range: -7.3076
Max Act: 6.7451. Min Act: -0.1700
Data Index: 5391096 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3076. Min Range: -7.3076
Max Act: 6.7139. Min Act: -0.1700
Data Index: 3512558 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3076. Min Range: -7.3076
Max Act: 6.7139. Min Act: -0.1700
Data Index: 5071833 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19