Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2586 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.5125. Min Act: -0.1700
Data Index: 5119669 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.4811. Min Act: -0.1700
Data Index: 1228752 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.4498. Min Act: -0.1700
Data Index: 1629006 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.4498. Min Act: -0.1700
Data Index: 1781351 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.4498. Min Act: -0.1700
Data Index: 7553975 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.4498. Min Act: -0.1700
Data Index: 2420472 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.4185. Min Act: -0.1700
Data Index: 3831471 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.4185. Min Act: -0.1700
Data Index: 1302888 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.3871. Min Act: -0.1700
Data Index: 8359471 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.1672. Min Act: -0.1700
Data Index: 547717 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.1357. Min Act: -0.1700
Data Index: 3298075 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.1515. Min Act: -0.1700
Data Index: 6045092 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.1357. Min Act: -0.1700
Data Index: 6027926 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.1515. Min Act: -0.1700
Data Index: 1255261 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.1357. Min Act: -0.1700
Data Index: 2361996 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.1357. Min Act: -0.1700
Data Index: 3240821 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.1357. Min Act: -0.1700
Data Index: 3298828 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.1357. Min Act: -0.1700
Data Index: 3928970 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.1357. Min Act: -0.1700
Data Index: 3937462 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5125. Min Range: -3.5125
Max Act: 3.1357. Min Act: -0.1700
Data Index: 5681697 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19