Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3220 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5837. Min Range: -10.5837
Max Act: 10.5837. Min Act: -0.1700
Data Index: 78392 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5837. Min Range: -10.5837
Max Act: 10.5212. Min Act: -0.1700
Data Index: 8384641 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5837. Min Range: -10.5837
Max Act: 10.3337. Min Act: -0.1700
Data Index: 4340348 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5837. Min Range: -10.5837
Max Act: 10.1462. Min Act: -0.1700
Data Index: 5235036 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5837. Min Range: -10.5837
Max Act: 10.1462. Min Act: -0.1700
Data Index: 5301794 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5837. Min Range: -10.5837
Max Act: 10.1462. Min Act: -0.1700
Data Index: 413488 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5837. Min Range: -10.5837
Max Act: 10.0212. Min Act: -0.1700
Data Index: 5601571 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5837. Min Range: -10.5837
Max Act: 10.0212. Min Act: -0.1700
Data Index: 4472191 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5837. Min Range: -10.5837
Max Act: 9.9587. Min Act: -0.1700
Data Index: 1228360 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5837. Min Range: -10.5837
Max Act: 9.8962. Min Act: -0.1700
Data Index: 4551622 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5837. Min Range: -10.5837
Max Act: 9.8962. Min Act: -0.1700
Data Index: 5365089 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5837. Min Range: -10.5837
Max Act: 9.8337. Min Act: -0.1700
Data Index: 4551621 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5837. Min Range: -10.5837
Max Act: 9.8337. Min Act: -0.1700
Data Index: 3631030 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5837. Min Range: -10.5837
Max Act: 9.8337. Min Act: -0.1700
Data Index: 372365 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5837. Min Range: -10.5837
Max Act: 9.7712. Min Act: -0.1700
Data Index: 5930414 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5837. Min Range: -10.5837
Max Act: 9.7712. Min Act: -0.1700
Data Index: 6211692 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5837. Min Range: -10.5837
Max Act: 9.7087. Min Act: -0.1700
Data Index: 5598668 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5837. Min Range: -10.5837
Max Act: 9.7087. Min Act: -0.1700
Data Index: 26821 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5837. Min Range: -10.5837
Max Act: 9.7712. Min Act: -0.1700
Data Index: 3966671 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5837. Min Range: -10.5837
Max Act: 9.7087. Min Act: -0.1700
Data Index: 3643316 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19