Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2571 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.4187. Min Act: -0.1700
Data Index: 8740054 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.4187. Min Act: -0.1700
Data Index: 7529031 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.2937. Min Act: -0.1700
Data Index: 8261348 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.3562. Min Act: -0.1700
Data Index: 2447363 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.3249. Min Act: -0.1700
Data Index: 3419797 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.3249. Min Act: -0.1700
Data Index: 2472698 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1999. Min Act: -0.1700
Data Index: 2415344 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1999. Min Act: -0.1700
Data Index: 7375542 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1999. Min Act: -0.1700
Data Index: 7068316 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1999. Min Act: -0.1700
Data Index: 7019280 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1687. Min Act: -0.1700
Data Index: 5375644 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1687. Min Act: -0.1700
Data Index: 3695300 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1687. Min Act: -0.1700
Data Index: 2775887 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1687. Min Act: -0.1700
Data Index: 2447362 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1374. Min Act: -0.1700
Data Index: 8665886 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1687. Min Act: -0.1700
Data Index: 3985332 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1999. Min Act: -0.1700
Data Index: 5922007 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1374. Min Act: -0.1700
Data Index: 3033426 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1374. Min Act: -0.1700
Data Index: 3292066 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1374. Min Act: -0.1700
Data Index: 2205445 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19