Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3602 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6016. Min Range: -7.6016
Max Act: 7.6016. Min Act: -0.1700
Data Index: 1985473 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6016. Min Range: -7.6016
Max Act: 7.2891. Min Act: -0.1700
Data Index: 2491290 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6016. Min Range: -7.6016
Max Act: 7.2579. Min Act: -0.1700
Data Index: 882354 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6016. Min Range: -7.6016
Max Act: 7.2579. Min Act: -0.1700
Data Index: 1770752 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6016. Min Range: -7.6016
Max Act: 7.1954. Min Act: -0.1700
Data Index: 4800388 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6016. Min Range: -7.6016
Max Act: 7.1954. Min Act: -0.1700
Data Index: 4696594 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6016. Min Range: -7.6016
Max Act: 6.9141. Min Act: -0.1700
Data Index: 3745401 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6016. Min Range: -7.6016
Max Act: 6.8829. Min Act: -0.1700
Data Index: 6876267 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6016. Min Range: -7.6016
Max Act: 6.8516. Min Act: -0.1700
Data Index: 7846623 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6016. Min Range: -7.6016
Max Act: 6.8516. Min Act: -0.1700
Data Index: 4526264 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6016. Min Range: -7.6016
Max Act: 6.8204. Min Act: -0.1700
Data Index: 4344027 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6016. Min Range: -7.6016
Max Act: 6.8204. Min Act: -0.1700
Data Index: 3397313 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6016. Min Range: -7.6016
Max Act: 6.7891. Min Act: -0.1700
Data Index: 7188092 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6016. Min Range: -7.6016
Max Act: 6.7891. Min Act: -0.1700
Data Index: 3076201 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6016. Min Range: -7.6016
Max Act: 6.7579. Min Act: -0.1700
Data Index: 835010 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6016. Min Range: -7.6016
Max Act: 6.7266. Min Act: -0.1700
Data Index: 3302826 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6016. Min Range: -7.6016
Max Act: 6.7266. Min Act: -0.1700
Data Index: 2459578 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6016. Min Range: -7.6016
Max Act: 6.6954. Min Act: -0.1700
Data Index: 6103039 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6016. Min Range: -7.6016
Max Act: 6.6641. Min Act: -0.1700
Data Index: 5231924 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6016. Min Range: -7.6016
Max Act: 6.6641. Min Act: -0.1700
Data Index: 6686222 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19