Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4524 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.8567. Min Act: -0.1700
Data Index: 3948449 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.8255. Min Act: -0.1700
Data Index: 8342469 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.7317. Min Act: -0.1700
Data Index: 7233412 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.7317. Min Act: -0.1700
Data Index: 7854826 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.7005. Min Act: -0.1700
Data Index: 2699840 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.7005. Min Act: -0.1700
Data Index: 7983416 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.6692. Min Act: -0.1700
Data Index: 1394705 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.6692. Min Act: -0.1700
Data Index: 3574550 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.6380. Min Act: -0.1700
Data Index: 6189809 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.6380. Min Act: -0.1693
Data Index: 4466986 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.6692. Min Act: -0.1700
Data Index: 600054 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.6380. Min Act: -0.1700
Data Index: 4906503 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.6067. Min Act: -0.1700
Data Index: 5523481 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.6067. Min Act: -0.1700
Data Index: 259942 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.6067. Min Act: -0.1700
Data Index: 2699845 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.5442. Min Act: -0.1700
Data Index: 8045024 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.5442. Min Act: -0.1700
Data Index: 5590600 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.5755. Min Act: -0.1700
Data Index: 2810025 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.5442. Min Act: -0.1700
Data Index: 2477709 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8567. Min Range: -6.8567
Max Act: 6.5442. Min Act: -0.1700
Data Index: 4037089 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19