Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5830 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1567. Min Range: -7.1567
Max Act: 7.1567. Min Act: -0.1700
Data Index: 7427722 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1567. Min Range: -7.1567
Max Act: 7.0942. Min Act: -0.1700
Data Index: 5374800 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1567. Min Range: -7.1567
Max Act: 7.0630. Min Act: -0.1700
Data Index: 359062 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1567. Min Range: -7.1567
Max Act: 7.0005. Min Act: -0.1700
Data Index: 3346783 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1567. Min Range: -7.1567
Max Act: 6.9692. Min Act: -0.1700
Data Index: 3001725 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1567. Min Range: -7.1567
Max Act: 6.9380. Min Act: -0.1700
Data Index: 2858460 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1567. Min Range: -7.1567
Max Act: 6.8442. Min Act: -0.1700
Data Index: 8669537 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1567. Min Range: -7.1567
Max Act: 6.8130. Min Act: -0.1700
Data Index: 490731 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1567. Min Range: -7.1567
Max Act: 6.8130. Min Act: -0.1700
Data Index: 4418231 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1567. Min Range: -7.1567
Max Act: 6.8130. Min Act: -0.1700
Data Index: 1436449 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1567. Min Range: -7.1567
Max Act: 6.7817. Min Act: -0.1700
Data Index: 8052394 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1567. Min Range: -7.1567
Max Act: 6.6567. Min Act: -0.1700
Data Index: 5656465 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1567. Min Range: -7.1567
Max Act: 6.6567. Min Act: -0.1700
Data Index: 7337906 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1567. Min Range: -7.1567
Max Act: 6.6567. Min Act: -0.1700
Data Index: 6398830 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1567. Min Range: -7.1567
Max Act: 6.6567. Min Act: -0.1700
Data Index: 5537881 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1567. Min Range: -7.1567
Max Act: 6.6567. Min Act: -0.1700
Data Index: 2998052 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1567. Min Range: -7.1567
Max Act: 6.6567. Min Act: -0.1700
Data Index: 5919526 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1567. Min Range: -7.1567
Max Act: 6.6255. Min Act: -0.1700
Data Index: 3480650 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1567. Min Range: -7.1567
Max Act: 6.5942. Min Act: -0.1700
Data Index: 7006704 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1567. Min Range: -7.1567
Max Act: 6.6255. Min Act: -0.1700
Data Index: 4378697 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19