Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3967 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.3857. Min Act: -0.1700
Data Index: 39626 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.3230. Min Act: -0.1700
Data Index: 8788978 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.3073. Min Act: -0.1700
Data Index: 4709734 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.3387. Min Act: -0.1700
Data Index: 5559364 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.2916. Min Act: -0.1700
Data Index: 3855672 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.2445. Min Act: -0.1700
Data Index: 8339065 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.2445. Min Act: -0.1700
Data Index: 7403582 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.2602. Min Act: -0.1700
Data Index: 8397389 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.2130. Min Act: -0.1700
Data Index: 8530140 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.1816. Min Act: -0.1700
Data Index: 6557195 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.1973. Min Act: -0.1700
Data Index: 2529692 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.1658. Min Act: -0.1700
Data Index: 6421642 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.1501. Min Act: -0.1700
Data Index: 3741967 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.1816. Min Act: -0.1700
Data Index: 1434107 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.1501. Min Act: -0.1700
Data Index: 6717764 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.1816. Min Act: -0.1700
Data Index: 8214379 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.1501. Min Act: -0.1700
Data Index: 5598084 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.1658. Min Act: -0.1700
Data Index: 5222470 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.1658. Min Act: -0.1700
Data Index: 7141148 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3857. Min Range: -3.3857
Max Act: 3.1501. Min Act: -0.1700
Data Index: 7195746 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19