Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3487 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.7041. Min Act: -0.1700
Data Index: 3380148 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.6728. Min Act: -0.1700
Data Index: 1641774 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.6728. Min Act: -0.1700
Data Index: 3657547 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.6416. Min Act: -0.1700
Data Index: 7907238 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.6103. Min Act: -0.1700
Data Index: 2948509 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.5478. Min Act: -0.1700
Data Index: 6157278 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.4228. Min Act: -0.1700
Data Index: 2831443 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.3916. Min Act: -0.1700
Data Index: 5557477 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.3603. Min Act: -0.1700
Data Index: 459277 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.3291. Min Act: -0.1700
Data Index: 1030812 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.2353. Min Act: -0.1700
Data Index: 6389060 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.2041. Min Act: -0.1700
Data Index: 2363227 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.2041. Min Act: -0.1700
Data Index: 7476642 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.0791. Min Act: -0.1700
Data Index: 4838846 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.0791. Min Act: -0.1700
Data Index: 6305147 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.0791. Min Act: -0.1700
Data Index: 4430935 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.0478. Min Act: -0.1700
Data Index: 6517388 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.0166. Min Act: -0.1700
Data Index: 1603193 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7041. Min Range: -7.7041
Max Act: 7.0166. Min Act: -0.1700
Data Index: 7522575 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7041. Min Range: -7.7041
Max Act: 6.9853. Min Act: -0.1700
Data Index: 7321567 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19