Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5103 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1951. Min Range: -9.1951
Max Act: 9.1951. Min Act: -0.1700
Data Index: 7277676 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.7576. Min Act: -0.1700
Data Index: 3615053 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.5701. Min Act: -0.1700
Data Index: 6606466 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.4451. Min Act: -0.1700
Data Index: 3198657 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.5076. Min Act: -0.1700
Data Index: 5861722 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.5076. Min Act: -0.1700
Data Index: 4799910 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.5076. Min Act: -0.1700
Data Index: 484515 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.4451. Min Act: -0.1700
Data Index: 2932766 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.4451. Min Act: -0.1700
Data Index: 2925730 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.4451. Min Act: -0.1700
Data Index: 2329966 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.4451. Min Act: -0.1700
Data Index: 8526877 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.4451. Min Act: -0.1700
Data Index: 3141014 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.3826. Min Act: -0.1700
Data Index: 1219634 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.3826. Min Act: -0.1700
Data Index: 4451019 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.3826. Min Act: -0.1700
Data Index: 5666433 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.3826. Min Act: -0.1700
Data Index: 4542277 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.3201. Min Act: -0.1700
Data Index: 6082711 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.3826. Min Act: -0.1700
Data Index: 6522036 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.3826. Min Act: -0.1700
Data Index: 2870049 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1951. Min Range: -9.1951
Max Act: 8.3826. Min Act: -0.1700
Data Index: 878382 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19