Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3626 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0297. Min Range: -5.0297
Max Act: 5.0297. Min Act: -0.1700
Data Index: 3434329 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.9047. Min Act: -0.1700
Data Index: 5098966 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.8735. Min Act: -0.1700
Data Index: 2626455 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.9360. Min Act: -0.1700
Data Index: 172576 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.8422. Min Act: -0.1700
Data Index: 5516665 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.8422. Min Act: -0.1700
Data Index: 3434338 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.8110. Min Act: -0.1700
Data Index: 5474225 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.7797. Min Act: -0.1700
Data Index: 5747534 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.7485. Min Act: -0.1700
Data Index: 5098978 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.7172. Min Act: -0.1700
Data Index: 5747536 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.7172. Min Act: -0.1700
Data Index: 5098988 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.6860. Min Act: -0.1700
Data Index: 5747520 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.6860. Min Act: -0.1700
Data Index: 7703706 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.6547. Min Act: -0.1700
Data Index: 4584162 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.6547. Min Act: -0.1700
Data Index: 3434340 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.6860. Min Act: -0.1700
Data Index: 755311 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.6860. Min Act: -0.1700
Data Index: 5747535 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.6547. Min Act: -0.1700
Data Index: 5747519 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.6860. Min Act: -0.1700
Data Index: 3434339 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0297. Min Range: -5.0297
Max Act: 4.6547. Min Act: -0.1700
Data Index: 8438197 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19