Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1522 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.7611. Min Act: -0.1700
Data Index: 3719259 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.4799. Min Act: -0.1700
Data Index: 5123203 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.4799. Min Act: -0.1700
Data Index: 4060253 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.4174. Min Act: -0.1700
Data Index: 7485197 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.4174. Min Act: -0.1700
Data Index: 4256416 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.4174. Min Act: -0.1700
Data Index: 3351646 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.3236. Min Act: -0.1700
Data Index: 7690550 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.2924. Min Act: -0.1700
Data Index: 274351 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.3236. Min Act: -0.1700
Data Index: 4659970 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.2611. Min Act: -0.1700
Data Index: 4942254 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.2924. Min Act: -0.1700
Data Index: 8530748 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.2924. Min Act: -0.1700
Data Index: 1382569 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.2924. Min Act: -0.1700
Data Index: 5204152 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.2611. Min Act: -0.1700
Data Index: 3780930 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.2611. Min Act: -0.1700
Data Index: 1990149 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.2299. Min Act: -0.1700
Data Index: 2736702 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.2299. Min Act: -0.1700
Data Index: 7838014 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.2299. Min Act: -0.1700
Data Index: 3652893 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.2299. Min Act: -0.1700
Data Index: 7986189 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7611. Min Range: -5.7611
Max Act: 5.2299. Min Act: -0.1700
Data Index: 2084437 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19