Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3402 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.4062. Min Act: -0.1700
Data Index: 3190585 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.4374. Min Act: -0.1700
Data Index: 8173024 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.4062. Min Act: -0.1700
Data Index: 5781875 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.3749. Min Act: -0.1700
Data Index: 8255858 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.3437. Min Act: -0.1700
Data Index: 7082817 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.3437. Min Act: -0.1700
Data Index: 8470626 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.2499. Min Act: -0.1700
Data Index: 3095926 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.2812. Min Act: -0.1700
Data Index: 6975287 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.1874. Min Act: -0.1700
Data Index: 887065 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.2186. Min Act: -0.1700
Data Index: 2311562 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.2499. Min Act: -0.1700
Data Index: 3894008 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.2186. Min Act: -0.1700
Data Index: 2409883 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.1874. Min Act: -0.1700
Data Index: 8154931 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.1561. Min Act: -0.1700
Data Index: 3824760 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.2186. Min Act: -0.1700
Data Index: 7428920 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.1561. Min Act: -0.1700
Data Index: 3590709 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.1874. Min Act: -0.1700
Data Index: 3387294 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.1874. Min Act: -0.1700
Data Index: 4687250 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.1874. Min Act: -0.1700
Data Index: 3093578 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.1874. Min Act: -0.1700
Data Index: 110700 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19