Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 819 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2451. Min Range: -6.2451
Max Act: 6.2451. Min Act: -0.1700
Data Index: 6480362 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2451. Min Range: -6.2451
Max Act: 6.0263. Min Act: -0.1700
Data Index: 2283109 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.9951. Min Act: -0.1700
Data Index: 6977581 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.9638. Min Act: -0.1700
Data Index: 6182588 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.9013. Min Act: -0.1700
Data Index: 7607875 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8701. Min Act: -0.1700
Data Index: 4271166 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8388. Min Act: -0.1700
Data Index: 1113997 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8388. Min Act: -0.1700
Data Index: 19848 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8076. Min Act: -0.1700
Data Index: 1553238 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8076. Min Act: -0.1700
Data Index: 2775521 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8076. Min Act: -0.1700
Data Index: 8205078 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8076. Min Act: -0.1700
Data Index: 8173714 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.7763. Min Act: -0.1700
Data Index: 4795508 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.7763. Min Act: -0.1700
Data Index: 3277229 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.7763. Min Act: -0.1700
Data Index: 3968432 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.7451. Min Act: -0.1700
Data Index: 2723241 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.7451. Min Act: -0.1700
Data Index: 1366965 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.7763. Min Act: -0.1700
Data Index: 6294056 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.7451. Min Act: -0.1700
Data Index: 4937709 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.7138. Min Act: -0.1700
Data Index: 3062194 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19