Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4643 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.3543. Min Act: -0.1700
Data Index: 6568031 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.2918. Min Act: -0.1700
Data Index: 5755258 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.2293. Min Act: -0.1700
Data Index: 2962156 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.2293. Min Act: -0.1700
Data Index: 1086740 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.1980. Min Act: -0.1700
Data Index: 1362844 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.1980. Min Act: -0.1700
Data Index: 7435229 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.1668. Min Act: -0.1700
Data Index: 6864259 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.1668. Min Act: -0.1700
Data Index: 6554868 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.1355. Min Act: -0.1700
Data Index: 7339934 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.1355. Min Act: -0.1700
Data Index: 5934675 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.1042. Min Act: -0.1700
Data Index: 1957577 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.1042. Min Act: -0.1700
Data Index: 8615002 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.1042. Min Act: -0.1700
Data Index: 7608856 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.1042. Min Act: -0.1700
Data Index: 3412152 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.0730. Min Act: -0.1700
Data Index: 4007927 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.1042. Min Act: -0.1700
Data Index: 5814386 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.1042. Min Act: -0.1700
Data Index: 1647646 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.0730. Min Act: -0.1700
Data Index: 2644123 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.0417. Min Act: -0.1700
Data Index: 5207030 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3543. Min Range: -4.3543
Max Act: 4.0730. Min Act: -0.1700
Data Index: 2508035 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19