Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2410 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.6817. Min Range: -12.6817
Max Act: 12.6817. Min Act: -0.1700
Data Index: 5647923 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.6817. Min Range: -12.6817
Max Act: 12.6192. Min Act: -0.1700
Data Index: 6590461 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.6817. Min Range: -12.6817
Max Act: 12.4317. Min Act: -0.1700
Data Index: 2053993 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.6817. Min Range: -12.6817
Max Act: 12.2442. Min Act: -0.1700
Data Index: 2732718 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.6817. Min Range: -12.6817
Max Act: 12.1192. Min Act: -0.1700
Data Index: 4431202 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.6817. Min Range: -12.6817
Max Act: 11.8692. Min Act: -0.1700
Data Index: 7329537 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.6817. Min Range: -12.6817
Max Act: 11.8067. Min Act: -0.1700
Data Index: 6990342 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.6817. Min Range: -12.6817
Max Act: 11.7442. Min Act: -0.1700
Data Index: 2734743 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.6817. Min Range: -12.6817
Max Act: 11.8067. Min Act: -0.1700
Data Index: 1491722 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.6817. Min Range: -12.6817
Max Act: 11.7442. Min Act: -0.1700
Data Index: 6855921 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.6817. Min Range: -12.6817
Max Act: 11.6817. Min Act: -0.1700
Data Index: 3108760 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.6817. Min Range: -12.6817
Max Act: 11.6192. Min Act: -0.1700
Data Index: 4108661 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.6817. Min Range: -12.6817
Max Act: 11.6817. Min Act: -0.1700
Data Index: 745247 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.6817. Min Range: -12.6817
Max Act: 11.6817. Min Act: -0.1700
Data Index: 4795312 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.6817. Min Range: -12.6817
Max Act: 11.6192. Min Act: -0.1700
Data Index: 8784302 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.6817. Min Range: -12.6817
Max Act: 11.6192. Min Act: -0.1700
Data Index: 6450274 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.6817. Min Range: -12.6817
Max Act: 11.6817. Min Act: -0.1700
Data Index: 10159 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.6817. Min Range: -12.6817
Max Act: 11.5567. Min Act: -0.1700
Data Index: 7932616 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.6817. Min Range: -12.6817
Max Act: 11.4942. Min Act: -0.1700
Data Index: 1677227 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.6817. Min Range: -12.6817
Max Act: 11.6192. Min Act: -0.1700
Data Index: 7844534 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19