Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3951 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.8837. Min Act: -0.1700
Data Index: 7061149 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.8495. Min Act: -0.1700
Data Index: 4209420 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.8152. Min Act: -0.1700
Data Index: 8256572 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.7980. Min Act: -0.1650
Data Index: 5276966 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.8152. Min Act: -0.1699
Data Index: 3641834 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.7635. Min Act: -0.1695
Data Index: 1459384 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.7462. Min Act: -0.1699
Data Index: 4178462 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.7462. Min Act: -0.1698
Data Index: 6755872 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.7290. Min Act: -0.1699
Data Index: 6632961 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.7290. Min Act: -0.1689
Data Index: 2864372 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.7290. Min Act: -0.1673
Data Index: 674819 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.6769. Min Act: -0.1669
Data Index: 4490351 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.6421. Min Act: -0.1700
Data Index: 3038749 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.6421. Min Act: -0.1700
Data Index: 2734116 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.6073. Min Act: -0.1699
Data Index: 674817 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.6073. Min Act: -0.1699
Data Index: 7021536 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.6073. Min Act: -0.1700
Data Index: 2590390 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.5898. Min Act: -0.1692
Data Index: 3641833 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.5898. Min Act: -0.1689
Data Index: 3474639 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8837. Min Range: -1.8837
Max Act: 1.5898. Min Act: -0.1700
Data Index: 5325083 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19