Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1979 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.6514. Min Act: -0.1700
Data Index: 4193560 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.5576. Min Act: -0.1700
Data Index: 7731077 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.3389. Min Act: -0.1700
Data Index: 53955 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.2764. Min Act: -0.1700
Data Index: 843731 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.2451. Min Act: -0.1700
Data Index: 3288472 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.2139. Min Act: -0.1700
Data Index: 1300600 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.1826. Min Act: -0.1700
Data Index: 7358450 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.1826. Min Act: -0.1700
Data Index: 7032523 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.1826. Min Act: -0.1700
Data Index: 3260605 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.1514. Min Act: -0.1700
Data Index: 1300601 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.1514. Min Act: -0.1700
Data Index: 509075 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.1514. Min Act: -0.1700
Data Index: 7032526 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.1201. Min Act: -0.1700
Data Index: 6874210 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.0889. Min Act: -0.1700
Data Index: 3783024 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.0576. Min Act: -0.1700
Data Index: 3252114 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.0889. Min Act: -0.1700
Data Index: 3783023 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.0576. Min Act: -0.1700
Data Index: 509070 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.0576. Min Act: -0.1700
Data Index: 2238542 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.0264. Min Act: -0.1700
Data Index: 8162644 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6514. Min Range: -6.6514
Max Act: 6.0264. Min Act: -0.1700
Data Index: 4014399 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19