Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1787 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.5519. Min Act: -0.1700
Data Index: 1603585 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.4581. Min Act: -0.1700
Data Index: 5061201 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.3956. Min Act: -0.1700
Data Index: 5098747 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.2706. Min Act: -0.1700
Data Index: 34039 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.2394. Min Act: -0.1700
Data Index: 7190091 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.2394. Min Act: -0.1700
Data Index: 7315697 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.2081. Min Act: -0.1700
Data Index: 6598061 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.2394. Min Act: -0.1700
Data Index: 5577440 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.2394. Min Act: -0.1700
Data Index: 7993830 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.2081. Min Act: -0.1700
Data Index: 6067138 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.2081. Min Act: -0.1700
Data Index: 2389774 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.1456. Min Act: -0.1700
Data Index: 1158278 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.1769. Min Act: -0.1700
Data Index: 171803 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.1456. Min Act: -0.1700
Data Index: 2372075 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.1456. Min Act: -0.1700
Data Index: 4304589 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.1456. Min Act: -0.1700
Data Index: 1000759 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.1144. Min Act: -0.1700
Data Index: 2125548 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.1144. Min Act: -0.1700
Data Index: 111553 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.1456. Min Act: -0.1700
Data Index: 2200486 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.1456. Min Act: -0.1700
Data Index: 5380744 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19