Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4136 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1537. Min Range: -3.1537
Max Act: 3.1537. Min Act: -0.1700
Data Index: 391877 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1537. Min Range: -3.1537
Max Act: 3.0434. Min Act: -0.1700
Data Index: 5555724 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1537. Min Range: -3.1537
Max Act: 3.0276. Min Act: -0.1700
Data Index: 1742373 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1537. Min Range: -3.1537
Max Act: 3.0118. Min Act: -0.1700
Data Index: 6841855 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1537. Min Range: -3.1537
Max Act: 3.0118. Min Act: -0.1700
Data Index: 5201115 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1537. Min Range: -3.1537
Max Act: 3.0118. Min Act: -0.1700
Data Index: 507492 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1537. Min Range: -3.1537
Max Act: 3.0118. Min Act: -0.1700
Data Index: 8161699 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1537. Min Range: -3.1537
Max Act: 2.9960. Min Act: -0.1700
Data Index: 8124068 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1537. Min Range: -3.1537
Max Act: 2.9644. Min Act: -0.1700
Data Index: 3674156 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1537. Min Range: -3.1537
Max Act: 2.9485. Min Act: -0.1700
Data Index: 2147027 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1537. Min Range: -3.1537
Max Act: 2.9327. Min Act: -0.1700
Data Index: 6454302 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1537. Min Range: -3.1537
Max Act: 2.9169. Min Act: -0.1700
Data Index: 5201114 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1537. Min Range: -3.1537
Max Act: 2.9169. Min Act: -0.1700
Data Index: 8717204 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1537. Min Range: -3.1537
Max Act: 2.9169. Min Act: -0.1700
Data Index: 497829 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1537. Min Range: -3.1537
Max Act: 2.8851. Min Act: -0.1700
Data Index: 2153159 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1537. Min Range: -3.1537
Max Act: 2.8851. Min Act: -0.1700
Data Index: 7373123 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1537. Min Range: -3.1537
Max Act: 2.8851. Min Act: -0.1700
Data Index: 2053 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1537. Min Range: -3.1537
Max Act: 2.8851. Min Act: -0.1700
Data Index: 4828191 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1537. Min Range: -3.1537
Max Act: 2.8693. Min Act: -0.1700
Data Index: 6769704 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1537. Min Range: -3.1537
Max Act: 2.8851. Min Act: -0.1700
Data Index: 5215773 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19