Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2916 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.3830. Min Act: -0.1700
Data Index: 4707813 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.3203. Min Act: -0.1700
Data Index: 432576 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.3203. Min Act: -0.1700
Data Index: 4193821 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.3046. Min Act: -0.1700
Data Index: 5972869 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.3046. Min Act: -0.1700
Data Index: 3447248 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.3046. Min Act: -0.1700
Data Index: 5325998 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.2260. Min Act: -0.1700
Data Index: 4795990 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.2260. Min Act: -0.1700
Data Index: 686630 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.2103. Min Act: -0.1700
Data Index: 608219 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.1946. Min Act: -0.1700
Data Index: 4017825 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.2103. Min Act: -0.1700
Data Index: 6982963 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.2103. Min Act: -0.1700
Data Index: 4440510 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.2260. Min Act: -0.1700
Data Index: 3285739 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.1946. Min Act: -0.1700
Data Index: 6485559 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.1946. Min Act: -0.1700
Data Index: 7162398 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.1946. Min Act: -0.1700
Data Index: 1621790 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.1946. Min Act: -0.1700
Data Index: 2741572 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.1789. Min Act: -0.1700
Data Index: 41606 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.1789. Min Act: -0.1700
Data Index: 1253838 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3830. Min Range: -3.3830
Max Act: 3.1474. Min Act: -0.1700
Data Index: 2417562 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19