Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 995 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.5953. Min Act: -0.1700
Data Index: 3695972 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.5953. Min Act: -0.1700
Data Index: 6119211 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.5641. Min Act: -0.1700
Data Index: 5564171 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.5328. Min Act: -0.1700
Data Index: 2395551 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.5328. Min Act: -0.1700
Data Index: 5736306 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.5016. Min Act: -0.1700
Data Index: 4400242 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.5016. Min Act: -0.1700
Data Index: 8048663 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.5016. Min Act: -0.1700
Data Index: 1851698 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.4391. Min Act: -0.1700
Data Index: 192438 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.4703. Min Act: -0.1700
Data Index: 4804509 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.4703. Min Act: -0.1700
Data Index: 4262223 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.4703. Min Act: -0.1700
Data Index: 893391 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.4703. Min Act: -0.1700
Data Index: 8149484 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.4078. Min Act: -0.1700
Data Index: 2597735 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.4703. Min Act: -0.1700
Data Index: 7053521 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.4391. Min Act: -0.1700
Data Index: 3138988 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.4078. Min Act: -0.1700
Data Index: 4601826 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.4078. Min Act: -0.1700
Data Index: 3535357 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.3766. Min Act: -0.1700
Data Index: 6793226 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5953. Min Range: -4.5953
Max Act: 4.4078. Min Act: -0.1700
Data Index: 5336226 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19