Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3573 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2983. Min Range: -4.2983
Max Act: 4.2983. Min Act: -0.1700
Data Index: 4842603 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2983. Min Range: -4.2983
Max Act: 4.2671. Min Act: -0.1700
Data Index: 4842602 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2983. Min Range: -4.2983
Max Act: 4.2358. Min Act: -0.1700
Data Index: 4440214 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2983. Min Range: -4.2983
Max Act: 4.1733. Min Act: -0.1700
Data Index: 304883 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2983. Min Range: -4.2983
Max Act: 4.2046. Min Act: -0.1700
Data Index: 6232845 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2983. Min Range: -4.2983
Max Act: 4.0795. Min Act: -0.1700
Data Index: 4842601 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2983. Min Range: -4.2983
Max Act: 4.0170. Min Act: -0.1700
Data Index: 6222379 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2983. Min Range: -4.2983
Max Act: 3.9858. Min Act: -0.1700
Data Index: 1800558 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2983. Min Range: -4.2983
Max Act: 3.9232. Min Act: -0.1700
Data Index: 5276684 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2983. Min Range: -4.2983
Max Act: 3.9545. Min Act: -0.1700
Data Index: 1792864 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2983. Min Range: -4.2983
Max Act: 3.9232. Min Act: -0.1700
Data Index: 4941460 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2983. Min Range: -4.2983
Max Act: 3.9232. Min Act: -0.1700
Data Index: 8503068 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2983. Min Range: -4.2983
Max Act: 3.9232. Min Act: -0.1700
Data Index: 4207592 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2983. Min Range: -4.2983
Max Act: 3.8920. Min Act: -0.1700
Data Index: 289554 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2983. Min Range: -4.2983
Max Act: 3.8920. Min Act: -0.1700
Data Index: 8390262 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2983. Min Range: -4.2983
Max Act: 3.8607. Min Act: -0.1700
Data Index: 2404785 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2983. Min Range: -4.2983
Max Act: 3.7982. Min Act: -0.1700
Data Index: 4857623 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2983. Min Range: -4.2983
Max Act: 3.8294. Min Act: -0.1700
Data Index: 1461623 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2983. Min Range: -4.2983
Max Act: 3.8294. Min Act: -0.1700
Data Index: 3004821 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2983. Min Range: -4.2983
Max Act: 3.7982. Min Act: -0.1700
Data Index: 1733438 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19