Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3035 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.3622. Min Act: -0.1700
Data Index: 1354052 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.3622. Min Act: -0.1700
Data Index: 5578946 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.2372. Min Act: -0.1700
Data Index: 2995047 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.2059. Min Act: -0.1700
Data Index: 488130 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.1747. Min Act: -0.1700
Data Index: 3569871 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.1747. Min Act: -0.1700
Data Index: 2084193 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.1434. Min Act: -0.1700
Data Index: 6941933 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.1434. Min Act: -0.1700
Data Index: 1853194 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.1121. Min Act: -0.1700
Data Index: 7430093 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.1434. Min Act: -0.1700
Data Index: 5582894 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.1121. Min Act: -0.1700
Data Index: 1611770 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.0809. Min Act: -0.1700
Data Index: 7490067 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.0809. Min Act: -0.1700
Data Index: 3660940 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.0809. Min Act: -0.1700
Data Index: 4356597 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.0809. Min Act: -0.1700
Data Index: 7159912 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.0496. Min Act: -0.1700
Data Index: 8378613 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.0184. Min Act: -0.1700
Data Index: 402297 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.0184. Min Act: -0.1700
Data Index: 4518044 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.0184. Min Act: -0.1700
Data Index: 7217846 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.0184. Min Act: -0.1700
Data Index: 7378898 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19