Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5782 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1913. Min Range: -6.1913
Max Act: 6.1913. Min Act: -0.1700
Data Index: 4766048 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1913. Min Range: -6.1913
Max Act: 6.0351. Min Act: -0.1700
Data Index: 2615650 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1913. Min Range: -6.1913
Max Act: 6.0663. Min Act: -0.1700
Data Index: 4052844 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1913. Min Range: -6.1913
Max Act: 5.9726. Min Act: -0.1700
Data Index: 7506015 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1913. Min Range: -6.1913
Max Act: 5.9726. Min Act: -0.1700
Data Index: 8623424 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1913. Min Range: -6.1913
Max Act: 5.9101. Min Act: -0.1700
Data Index: 992501 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1913. Min Range: -6.1913
Max Act: 5.8476. Min Act: -0.1700
Data Index: 2552181 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1913. Min Range: -6.1913
Max Act: 5.8163. Min Act: -0.1700
Data Index: 1090129 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1913. Min Range: -6.1913
Max Act: 5.7851. Min Act: -0.1700
Data Index: 802765 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1913. Min Range: -6.1913
Max Act: 5.8163. Min Act: -0.1700
Data Index: 3968609 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1913. Min Range: -6.1913
Max Act: 5.7538. Min Act: -0.1700
Data Index: 466509 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1913. Min Range: -6.1913
Max Act: 5.7538. Min Act: -0.1700
Data Index: 5952397 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1913. Min Range: -6.1913
Max Act: 5.7226. Min Act: -0.1700
Data Index: 802761 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1913. Min Range: -6.1913
Max Act: 5.6288. Min Act: -0.1700
Data Index: 802769 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1913. Min Range: -6.1913
Max Act: 5.5976. Min Act: -0.1700
Data Index: 766817 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1913. Min Range: -6.1913
Max Act: 5.6288. Min Act: -0.1700
Data Index: 5697402 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1913. Min Range: -6.1913
Max Act: 5.5976. Min Act: -0.1700
Data Index: 4484985 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1913. Min Range: -6.1913
Max Act: 5.5976. Min Act: -0.1700
Data Index: 7283501 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1913. Min Range: -6.1913
Max Act: 5.5663. Min Act: -0.1700
Data Index: 1911938 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1913. Min Range: -6.1913
Max Act: 5.5351. Min Act: -0.1700
Data Index: 8558506 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19