Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4823 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.6593. Min Act: -0.1700
Data Index: 4818927 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.4093. Min Act: -0.1700
Data Index: 2270224 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.4093. Min Act: -0.1700
Data Index: 3343236 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.4093. Min Act: -0.1700
Data Index: 5483456 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.3468. Min Act: -0.1700
Data Index: 456650 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.3468. Min Act: -0.1700
Data Index: 1083697 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.2843. Min Act: -0.1700
Data Index: 5761873 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.2843. Min Act: -0.1700
Data Index: 615893 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.2843. Min Act: -0.1700
Data Index: 4974991 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.1593. Min Act: -0.1700
Data Index: 1826055 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.2218. Min Act: -0.1700
Data Index: 4326108 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.2218. Min Act: -0.1700
Data Index: 4066464 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.1593. Min Act: -0.1700
Data Index: 3770153 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.1593. Min Act: -0.1700
Data Index: 1427310 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.1593. Min Act: -0.1700
Data Index: 257221 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.1593. Min Act: -0.1700
Data Index: 8389726 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.1593. Min Act: -0.1700
Data Index: 7610357 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.0968. Min Act: -0.1700
Data Index: 7815313 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.0968. Min Act: -0.1700
Data Index: 7574471 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6593. Min Range: -10.6593
Max Act: 10.0968. Min Act: -0.1700
Data Index: 6639862 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19