Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 83 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.1766. Min Act: -0.1700
Data Index: 1930735 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.1766. Min Act: -0.1700
Data Index: 6710356 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.1766. Min Act: -0.1700
Data Index: 8125911 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.1454. Min Act: -0.1700
Data Index: 4256253 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.1141. Min Act: -0.1700
Data Index: 8574251 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.1454. Min Act: -0.1700
Data Index: 114627 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.1141. Min Act: -0.1700
Data Index: 8530039 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.1141. Min Act: -0.1700
Data Index: 1476020 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.1141. Min Act: -0.1700
Data Index: 590555 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.1141. Min Act: -0.1700
Data Index: 8546006 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.1141. Min Act: -0.1700
Data Index: 8535379 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.1141. Min Act: -0.1700
Data Index: 1196920 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.1141. Min Act: -0.1700
Data Index: 6293082 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.1141. Min Act: -0.1700
Data Index: 5156524 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.1141. Min Act: -0.1700
Data Index: 4162048 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.1141. Min Act: -0.1700
Data Index: 4006439 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.1141. Min Act: -0.1700
Data Index: 630364 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.0829. Min Act: -0.1700
Data Index: 1600039 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.0516. Min Act: -0.1700
Data Index: 912178 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.0829. Min Act: -0.1700
Data Index: 1780843 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19