Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3562 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.5445. Min Act: -0.1700
Data Index: 8242152 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.5445. Min Act: -0.1700
Data Index: 2654166 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.5132. Min Act: -0.1699
Data Index: 3006405 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.4820. Min Act: -0.1700
Data Index: 7680774 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.4507. Min Act: -0.1700
Data Index: 3500658 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.3882. Min Act: -0.1700
Data Index: 3129431 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.3257. Min Act: -0.1700
Data Index: 4815074 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.3257. Min Act: -0.1700
Data Index: 4945427 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.2945. Min Act: -0.1700
Data Index: 1065344 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.2007. Min Act: -0.1700
Data Index: 6979764 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.2632. Min Act: -0.1700
Data Index: 1501550 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.2632. Min Act: -0.1700
Data Index: 1633381 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.2320. Min Act: -0.1700
Data Index: 3048387 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.2320. Min Act: -0.1700
Data Index: 496323 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.2320. Min Act: -0.1700
Data Index: 3857639 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.2632. Min Act: -0.1700
Data Index: 1997716 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.2007. Min Act: -0.1700
Data Index: 5300565 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.2320. Min Act: -0.1700
Data Index: 1502448 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.2007. Min Act: -0.1700
Data Index: 2540303 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5445. Min Range: -7.5445
Max Act: 7.2007. Min Act: -0.1700
Data Index: 3793262 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19