Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2803 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.3736. Min Act: -0.1700
Data Index: 6426153 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.3424. Min Act: -0.1700
Data Index: 1044016 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.2486. Min Act: -0.1700
Data Index: 4402693 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.3111. Min Act: -0.1700
Data Index: 6580384 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.2799. Min Act: -0.1700
Data Index: 5978831 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.2486. Min Act: -0.1700
Data Index: 6659898 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.2174. Min Act: -0.1700
Data Index: 5955168 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.2174. Min Act: -0.1700
Data Index: 7730804 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.1549. Min Act: -0.1700
Data Index: 1810437 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.1861. Min Act: -0.1700
Data Index: 3432451 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.1236. Min Act: -0.1700
Data Index: 287170 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.1236. Min Act: -0.1700
Data Index: 4885039 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.0924. Min Act: -0.1700
Data Index: 255163 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.0924. Min Act: -0.1700
Data Index: 4642431 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.0924. Min Act: -0.1700
Data Index: 2365699 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.0924. Min Act: -0.1700
Data Index: 2247409 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.0924. Min Act: -0.1700
Data Index: 2227914 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.0611. Min Act: -0.1700
Data Index: 7525288 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.0611. Min Act: -0.1700
Data Index: 250158 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.0299. Min Act: -0.1700
Data Index: 3461439 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19