Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3419 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.5600. Min Act: -0.1700
Data Index: 6062187 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.5439. Min Act: -0.1700
Data Index: 1522162 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.5116. Min Act: -0.1700
Data Index: 4622323 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.5277. Min Act: -0.1700
Data Index: 6840588 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.5277. Min Act: -0.1700
Data Index: 8173298 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.4954. Min Act: -0.1700
Data Index: 3339452 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.5116. Min Act: -0.1700
Data Index: 6343867 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.4791. Min Act: -0.1700
Data Index: 2137305 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.4467. Min Act: -0.1700
Data Index: 989321 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.4304. Min Act: -0.1700
Data Index: 216320 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.4304. Min Act: -0.1700
Data Index: 3188158 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.4304. Min Act: -0.1700
Data Index: 223250 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.4141. Min Act: -0.1700
Data Index: 3077162 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.3978. Min Act: -0.1700
Data Index: 3774480 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.4141. Min Act: -0.1700
Data Index: 2679532 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.4141. Min Act: -0.1700
Data Index: 5052410 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.4141. Min Act: -0.1700
Data Index: 1471038 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.4141. Min Act: -0.1700
Data Index: 1724252 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.3978. Min Act: -0.1700
Data Index: 7366487 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5600. Min Range: -2.5600
Max Act: 2.3978. Min Act: -0.1700
Data Index: 1709595 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19