Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5781 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.6682. Min Act: -0.1700
Data Index: 6465939 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.6057. Min Act: -0.1700
Data Index: 6884152 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.6057. Min Act: -0.1700
Data Index: 2556535 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.4807. Min Act: -0.1700
Data Index: 3296602 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.3870. Min Act: -0.1700
Data Index: 2366152 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.3870. Min Act: -0.1700
Data Index: 3769528 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.4182. Min Act: -0.1700
Data Index: 6046771 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.3870. Min Act: -0.1700
Data Index: 4907287 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.3245. Min Act: -0.1700
Data Index: 5316600 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.3245. Min Act: -0.1700
Data Index: 3785261 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.2620. Min Act: -0.1700
Data Index: 3811272 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.2620. Min Act: -0.1700
Data Index: 352312 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.2620. Min Act: -0.1700
Data Index: 5513513 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.2307. Min Act: -0.1700
Data Index: 1396522 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.2307. Min Act: -0.1700
Data Index: 427796 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.2307. Min Act: -0.1700
Data Index: 6057838 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.2307. Min Act: -0.1700
Data Index: 3723014 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.2620. Min Act: -0.1700
Data Index: 3934863 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.2307. Min Act: -0.1700
Data Index: 5869710 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6682. Min Range: -4.6682
Max Act: 4.2307. Min Act: -0.1700
Data Index: 3341488 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19