Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.5062. Min Act: -0.1700
Data Index: 1762173 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.3812. Min Act: -0.1700
Data Index: 3038043 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.3187. Min Act: -0.1700
Data Index: 5031553 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.2562. Min Act: -0.1700
Data Index: 7452875 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.2250. Min Act: -0.1700
Data Index: 7719085 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.1937. Min Act: -0.1700
Data Index: 5824972 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.1625. Min Act: -0.1700
Data Index: 4315489 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.1625. Min Act: -0.1700
Data Index: 2844178 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.1000. Min Act: -0.1700
Data Index: 6652904 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.1000. Min Act: -0.1700
Data Index: 8128689 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.0375. Min Act: -0.1700
Data Index: 5885603 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.0687. Min Act: -0.1700
Data Index: 913358 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.0687. Min Act: -0.1700
Data Index: 6153456 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.0375. Min Act: -0.1700
Data Index: 8084538 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.0375. Min Act: -0.1700
Data Index: 8097164 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.0375. Min Act: -0.1700
Data Index: 7057028 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.0375. Min Act: -0.1700
Data Index: 8544170 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.0375. Min Act: -0.1700
Data Index: 8790978 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.0375. Min Act: -0.1700
Data Index: 5930097 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.0375. Min Act: -0.1700
Data Index: 7624304 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19