Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3539 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2807. Min Range: -10.2807
Max Act: 10.2807. Min Act: -0.1700
Data Index: 3730112 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2807. Min Range: -10.2807
Max Act: 10.1557. Min Act: -0.1700
Data Index: 5574649 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2807. Min Range: -10.2807
Max Act: 10.0932. Min Act: -0.1700
Data Index: 404549 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2807. Min Range: -10.2807
Max Act: 9.9682. Min Act: -0.1700
Data Index: 3032610 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2807. Min Range: -10.2807
Max Act: 10.0307. Min Act: -0.1700
Data Index: 8557454 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2807. Min Range: -10.2807
Max Act: 9.9682. Min Act: -0.1700
Data Index: 2994557 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2807. Min Range: -10.2807
Max Act: 9.9682. Min Act: -0.1700
Data Index: 3621202 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2807. Min Range: -10.2807
Max Act: 9.9682. Min Act: -0.1700
Data Index: 969936 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2807. Min Range: -10.2807
Max Act: 10.0307. Min Act: -0.1700
Data Index: 4016111 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2807. Min Range: -10.2807
Max Act: 9.9682. Min Act: -0.1700
Data Index: 6740333 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2807. Min Range: -10.2807
Max Act: 9.9057. Min Act: -0.1700
Data Index: 982094 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2807. Min Range: -10.2807
Max Act: 9.9057. Min Act: -0.1700
Data Index: 4586782 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2807. Min Range: -10.2807
Max Act: 9.8432. Min Act: -0.1700
Data Index: 7374428 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2807. Min Range: -10.2807
Max Act: 9.8432. Min Act: -0.1700
Data Index: 8024923 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2807. Min Range: -10.2807
Max Act: 9.8432. Min Act: -0.1700
Data Index: 6855990 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2807. Min Range: -10.2807
Max Act: 9.7807. Min Act: -0.1700
Data Index: 5259423 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2807. Min Range: -10.2807
Max Act: 9.7807. Min Act: -0.1700
Data Index: 8211501 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2807. Min Range: -10.2807
Max Act: 9.7807. Min Act: -0.1700
Data Index: 7081945 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2807. Min Range: -10.2807
Max Act: 9.7182. Min Act: -0.1700
Data Index: 393703 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2807. Min Range: -10.2807
Max Act: 9.7182. Min Act: -0.1700
Data Index: 617239 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19