Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2944 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.2632. Min Act: -0.1700
Data Index: 1282964 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.2632. Min Act: -0.1700
Data Index: 2232700 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.2632. Min Act: -0.1700
Data Index: 964109 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.2475. Min Act: -0.1700
Data Index: 805495 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.2475. Min Act: -0.1700
Data Index: 4710789 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.2475. Min Act: -0.1700
Data Index: 5737369 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.2475. Min Act: -0.1700
Data Index: 3931306 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.2317. Min Act: -0.1700
Data Index: 1126032 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.2317. Min Act: -0.1700
Data Index: 3703515 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.2317. Min Act: -0.1700
Data Index: 7853197 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.2160. Min Act: -0.1700
Data Index: 4287608 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.2160. Min Act: -0.1700
Data Index: 6512508 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.2003. Min Act: -0.1700
Data Index: 4529446 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.2003. Min Act: -0.1700
Data Index: 1764325 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.2003. Min Act: -0.1700
Data Index: 6779305 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.1846. Min Act: -0.1700
Data Index: 5800120 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.1846. Min Act: -0.1700
Data Index: 1638560 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.1846. Min Act: -0.1700
Data Index: 2613408 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.1846. Min Act: -0.1700
Data Index: 5603436 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2632. Min Range: -3.2632
Max Act: 3.1846. Min Act: -0.1700
Data Index: 1912253 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19