Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3184 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.5340. Min Act: -0.1700
Data Index: 1073215 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.4204. Min Act: -0.1700
Data Index: 3933193 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.3058. Min Act: -0.1700
Data Index: 4451374 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.3058. Min Act: -0.1700
Data Index: 7942895 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.2894. Min Act: -0.1700
Data Index: 4548890 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.2729. Min Act: -0.1700
Data Index: 139648 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.2729. Min Act: -0.1700
Data Index: 5163775 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.2564. Min Act: -0.1700
Data Index: 5700289 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.2399. Min Act: -0.1700
Data Index: 4329360 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.2399. Min Act: -0.1700
Data Index: 934354 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.2399. Min Act: -0.1700
Data Index: 5320088 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.2233. Min Act: -0.1700
Data Index: 5986965 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.2233. Min Act: -0.1700
Data Index: 2333994 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.2233. Min Act: -0.1700
Data Index: 1851517 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.2068. Min Act: -0.1700
Data Index: 7740945 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.2068. Min Act: -0.1700
Data Index: 1769918 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.2068. Min Act: -0.1700
Data Index: 4070938 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.2068. Min Act: -0.1700
Data Index: 8367565 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.2068. Min Act: -0.1700
Data Index: 204130 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5340. Min Range: -2.5340
Max Act: 2.2068. Min Act: -0.1700
Data Index: 4878884 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19