Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 774 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.7573. Min Act: -0.1700
Data Index: 6380727 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.7260. Min Act: -0.1700
Data Index: 3813008 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.6948. Min Act: -0.1700
Data Index: 464787 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.5698. Min Act: -0.1700
Data Index: 5788653 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.6010. Min Act: -0.1700
Data Index: 6838976 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.5385. Min Act: -0.1700
Data Index: 8755897 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.5385. Min Act: -0.1700
Data Index: 2013698 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.5073. Min Act: -0.1700
Data Index: 5246353 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.5073. Min Act: -0.1700
Data Index: 5420076 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.4448. Min Act: -0.1700
Data Index: 2994766 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.4760. Min Act: -0.1700
Data Index: 6292254 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.4760. Min Act: -0.1700
Data Index: 4091702 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.4448. Min Act: -0.1700
Data Index: 1286552 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.4135. Min Act: -0.1700
Data Index: 5673166 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.4448. Min Act: -0.1700
Data Index: 2013697 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.4448. Min Act: -0.1700
Data Index: 1185200 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.4448. Min Act: -0.1700
Data Index: 8523920 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.4135. Min Act: -0.1700
Data Index: 3815065 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.4135. Min Act: -0.1700
Data Index: 5148321 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7573. Min Range: -4.7573
Max Act: 4.4135. Min Act: -0.1700
Data Index: 7067199 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19