Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1748 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0938. Min Act: -0.1700
Data Index: 2942403 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0938. Min Act: -0.1700
Data Index: 5838458 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0622. Min Act: -0.1700
Data Index: 4104139 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0622. Min Act: -0.1700
Data Index: 3829623 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0622. Min Act: -0.1700
Data Index: 2648029 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0622. Min Act: -0.1700
Data Index: 8043565 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0622. Min Act: -0.1700
Data Index: 6075842 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0622. Min Act: -0.1700
Data Index: 5926879 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0622. Min Act: -0.1700
Data Index: 4911388 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0938. Min Act: -0.1700
Data Index: 1355406 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0622. Min Act: -0.1700
Data Index: 4444590 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0622. Min Act: -0.1700
Data Index: 1044989 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0622. Min Act: -0.1700
Data Index: 3926166 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0307. Min Act: -0.1700
Data Index: 151016 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0307. Min Act: -0.1700
Data Index: 1825939 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0307. Min Act: -0.1700
Data Index: 1962901 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0307. Min Act: -0.1700
Data Index: 576693 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0307. Min Act: -0.1700
Data Index: 2162054 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0307. Min Act: -0.1700
Data Index: 3371712 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0938. Min Range: -3.0938
Max Act: 3.0307. Min Act: -0.1700
Data Index: 3777653 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19