Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.3116. Min Act: -0.1700
Data Index: 2320394 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.2178. Min Act: -0.1700
Data Index: 4295308 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.1866. Min Act: -0.1700
Data Index: 3024596 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0616. Min Act: -0.1700
Data Index: 7895213 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0616. Min Act: -0.1700
Data Index: 7728931 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0303. Min Act: -0.1700
Data Index: 2045771 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3116. Min Range: -5.3116
Max Act: 4.9991. Min Act: -0.1700
Data Index: 6038015 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0303. Min Act: -0.1700
Data Index: 4254578 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0303. Min Act: -0.1700
Data Index: 832439 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0303. Min Act: -0.1700
Data Index: 5217621 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3116. Min Range: -5.3116
Max Act: 4.9991. Min Act: -0.1700
Data Index: 4881900 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3116. Min Range: -5.3116
Max Act: 4.9991. Min Act: -0.1700
Data Index: 1911770 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3116. Min Range: -5.3116
Max Act: 4.9991. Min Act: -0.1700
Data Index: 5826447 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3116. Min Range: -5.3116
Max Act: 4.9991. Min Act: -0.1700
Data Index: 5343572 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3116. Min Range: -5.3116
Max Act: 4.9991. Min Act: -0.1700
Data Index: 3397405 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3116. Min Range: -5.3116
Max Act: 4.9991. Min Act: -0.1700
Data Index: 2570953 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3116. Min Range: -5.3116
Max Act: 4.9678. Min Act: -0.1700
Data Index: 4061339 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3116. Min Range: -5.3116
Max Act: 4.9678. Min Act: -0.1700
Data Index: 5040414 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3116. Min Range: -5.3116
Max Act: 4.9678. Min Act: -0.1700
Data Index: 1955319 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3116. Min Range: -5.3116
Max Act: 4.9678. Min Act: -0.1700
Data Index: 3648881 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19