Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4193 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.7068. Min Act: -0.1700
Data Index: 7946468 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.6130. Min Act: -0.1700
Data Index: 4999348 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.5505. Min Act: -0.1700
Data Index: 1138182 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.5193. Min Act: -0.1700
Data Index: 3424639 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.5193. Min Act: -0.1700
Data Index: 8424083 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.5193. Min Act: -0.1700
Data Index: 2887976 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.4880. Min Act: -0.1700
Data Index: 5736126 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.4880. Min Act: -0.1700
Data Index: 3669263 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.4568. Min Act: -0.1700
Data Index: 5820915 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.4568. Min Act: -0.1700
Data Index: 4432848 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.4568. Min Act: -0.1700
Data Index: 4938357 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.4255. Min Act: -0.1700
Data Index: 5553747 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.4255. Min Act: -0.1700
Data Index: 8170844 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.4255. Min Act: -0.1700
Data Index: 4001377 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.3943. Min Act: -0.1700
Data Index: 105365 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.3630. Min Act: -0.1700
Data Index: 8207674 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.3630. Min Act: -0.1700
Data Index: 191236 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.3630. Min Act: -0.1700
Data Index: 2114372 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.3318. Min Act: -0.1700
Data Index: 5391832 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.3005. Min Act: -0.1700
Data Index: 5844642 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19