Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1352 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3110. Min Range: -7.3110
Max Act: 7.3110. Min Act: -0.1700
Data Index: 5821089 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3110. Min Range: -7.3110
Max Act: 7.0297. Min Act: -0.1700
Data Index: 4647981 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3110. Min Range: -7.3110
Max Act: 6.9672. Min Act: -0.1700
Data Index: 7420697 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3110. Min Range: -7.3110
Max Act: 6.9985. Min Act: -0.1700
Data Index: 528984 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3110. Min Range: -7.3110
Max Act: 6.8735. Min Act: -0.1700
Data Index: 7416989 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3110. Min Range: -7.3110
Max Act: 6.8735. Min Act: -0.1700
Data Index: 6042628 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3110. Min Range: -7.3110
Max Act: 6.8422. Min Act: -0.1700
Data Index: 1348751 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3110. Min Range: -7.3110
Max Act: 6.8422. Min Act: -0.1700
Data Index: 2290314 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3110. Min Range: -7.3110
Max Act: 6.8735. Min Act: -0.1700
Data Index: 6100085 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3110. Min Range: -7.3110
Max Act: 6.8422. Min Act: -0.1700
Data Index: 7597021 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3110. Min Range: -7.3110
Max Act: 6.8110. Min Act: -0.1700
Data Index: 7964617 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3110. Min Range: -7.3110
Max Act: 6.8110. Min Act: -0.1700
Data Index: 6714503 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3110. Min Range: -7.3110
Max Act: 6.7797. Min Act: -0.1700
Data Index: 2798044 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3110. Min Range: -7.3110
Max Act: 6.7485. Min Act: -0.1700
Data Index: 5243742 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3110. Min Range: -7.3110
Max Act: 6.7485. Min Act: -0.1700
Data Index: 428457 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3110. Min Range: -7.3110
Max Act: 6.7485. Min Act: -0.1700
Data Index: 3878214 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3110. Min Range: -7.3110
Max Act: 6.7172. Min Act: -0.1700
Data Index: 5488832 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3110. Min Range: -7.3110
Max Act: 6.7172. Min Act: -0.1700
Data Index: 4368323 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3110. Min Range: -7.3110
Max Act: 6.6860. Min Act: -0.1700
Data Index: 4049886 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3110. Min Range: -7.3110
Max Act: 6.6860. Min Act: -0.1700
Data Index: 572873 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19