Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 508 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0155. Min Range: -3.0155
Max Act: 3.0155. Min Act: -0.1700
Data Index: 3422693 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.9997. Min Act: -0.1700
Data Index: 6584517 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.9522. Min Act: -0.1700
Data Index: 173407 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.9522. Min Act: -0.1700
Data Index: 8433616 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.9364. Min Act: -0.1700
Data Index: 1766612 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.9047. Min Act: -0.1700
Data Index: 1766601 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.8730. Min Act: -0.1700
Data Index: 721170 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.8889. Min Act: -0.1700
Data Index: 411112 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.8571. Min Act: -0.1700
Data Index: 8506897 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.9047. Min Act: -0.1700
Data Index: 8433607 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.8571. Min Act: -0.1700
Data Index: 8826023 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.8412. Min Act: -0.1700
Data Index: 8788725 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.8571. Min Act: -0.1700
Data Index: 8422146 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.8571. Min Act: -0.1700
Data Index: 5137643 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.8412. Min Act: -0.1700
Data Index: 1566259 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.8730. Min Act: -0.1700
Data Index: 5824791 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.8571. Min Act: -0.1700
Data Index: 5216573 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.8412. Min Act: -0.1700
Data Index: 693516 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.8253. Min Act: -0.1700
Data Index: 252089 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0155. Min Range: -3.0155
Max Act: 2.8571. Min Act: -0.1700
Data Index: 416086 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19