Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1890 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.7438. Min Act: -0.1700
Data Index: 3026968 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.7438. Min Act: -0.1700
Data Index: 3073337 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.6798. Min Act: -0.1700
Data Index: 7291143 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.6958. Min Act: -0.1700
Data Index: 4533116 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.6638. Min Act: -0.1700
Data Index: 6220888 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.6798. Min Act: -0.1700
Data Index: 7654069 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.6638. Min Act: -0.1700
Data Index: 6519726 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.6317. Min Act: -0.1700
Data Index: 6412781 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.6156. Min Act: -0.1700
Data Index: 4553815 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.6317. Min Act: -0.1700
Data Index: 543015 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.5512. Min Act: -0.1700
Data Index: 1185637 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.5673. Min Act: -0.1700
Data Index: 1488592 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.5673. Min Act: -0.1700
Data Index: 5446836 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.5673. Min Act: -0.1700
Data Index: 626330 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.5512. Min Act: -0.1700
Data Index: 829832 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.5512. Min Act: -0.1700
Data Index: 8279366 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.5673. Min Act: -0.1700
Data Index: 2667601 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.5512. Min Act: -0.1700
Data Index: 140375 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.5188. Min Act: -0.1700
Data Index: 6295101 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7438. Min Range: -2.7438
Max Act: 2.5350. Min Act: -0.1700
Data Index: 3137055 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19