Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3900 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2062. Min Range: -7.2062
Max Act: 7.2062. Min Act: -0.1700
Data Index: 4018635 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2062. Min Range: -7.2062
Max Act: 7.0187. Min Act: -0.1700
Data Index: 2282959 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.9249. Min Act: -0.1700
Data Index: 110106 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.9249. Min Act: -0.1700
Data Index: 7708552 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.8937. Min Act: -0.1700
Data Index: 128188 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.8937. Min Act: -0.1700
Data Index: 278014 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.8937. Min Act: -0.1700
Data Index: 7410163 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.8624. Min Act: -0.1700
Data Index: 5543284 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.8312. Min Act: -0.1700
Data Index: 2939141 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.8312. Min Act: -0.1700
Data Index: 8792498 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.7999. Min Act: -0.1700
Data Index: 7499703 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.7374. Min Act: -0.1700
Data Index: 741859 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.7062. Min Act: -0.1700
Data Index: 5192661 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.7062. Min Act: -0.1700
Data Index: 5049248 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.6749. Min Act: -0.1700
Data Index: 3140430 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.6749. Min Act: -0.1700
Data Index: 7726944 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.6437. Min Act: -0.1700
Data Index: 2393759 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.6437. Min Act: -0.1700
Data Index: 7966144 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.6124. Min Act: -0.1700
Data Index: 8613808 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.6437. Min Act: -0.1700
Data Index: 7417510 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19