Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3629 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.8914. Min Act: -0.1700
Data Index: 1131240 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.6101. Min Act: -0.1700
Data Index: 4922019 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.3601. Min Act: -0.1700
Data Index: 4977084 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.3601. Min Act: -0.1700
Data Index: 701485 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.3289. Min Act: -0.1700
Data Index: 4776515 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.3289. Min Act: -0.1700
Data Index: 5033851 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.3289. Min Act: -0.1700
Data Index: 7320251 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.2976. Min Act: -0.1700
Data Index: 315759 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.2976. Min Act: -0.1700
Data Index: 7791571 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.2976. Min Act: -0.1700
Data Index: 1475144 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.2664. Min Act: -0.1700
Data Index: 543472 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.2976. Min Act: -0.1700
Data Index: 3395637 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.2664. Min Act: -0.1700
Data Index: 7479240 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.2351. Min Act: -0.1700
Data Index: 3086943 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.2351. Min Act: -0.1700
Data Index: 6713435 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.2351. Min Act: -0.1700
Data Index: 5033853 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.2351. Min Act: -0.1700
Data Index: 576866 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.2351. Min Act: -0.1700
Data Index: 6292746 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.2039. Min Act: -0.1700
Data Index: 3765536 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8914. Min Range: -5.8914
Max Act: 5.2039. Min Act: -0.1700
Data Index: 1202956 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19