Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1225 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6482. Min Range: -7.6482
Max Act: 7.6482. Min Act: -0.1700
Data Index: 5972761 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6482. Min Range: -7.6482
Max Act: 7.5544. Min Act: -0.1700
Data Index: 823360 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6482. Min Range: -7.6482
Max Act: 7.4919. Min Act: -0.1700
Data Index: 1925743 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6482. Min Range: -7.6482
Max Act: 7.4607. Min Act: -0.1700
Data Index: 1905550 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6482. Min Range: -7.6482
Max Act: 7.2107. Min Act: -0.1700
Data Index: 5407897 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6482. Min Range: -7.6482
Max Act: 7.1794. Min Act: -0.1700
Data Index: 7331872 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6482. Min Range: -7.6482
Max Act: 7.1794. Min Act: -0.1700
Data Index: 79442 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6482. Min Range: -7.6482
Max Act: 7.1169. Min Act: -0.1700
Data Index: 7445624 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6482. Min Range: -7.6482
Max Act: 7.1169. Min Act: -0.1700
Data Index: 6912119 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6482. Min Range: -7.6482
Max Act: 7.1169. Min Act: -0.1700
Data Index: 921956 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6482. Min Range: -7.6482
Max Act: 7.0857. Min Act: -0.1700
Data Index: 2008271 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6482. Min Range: -7.6482
Max Act: 7.0544. Min Act: -0.1700
Data Index: 5900415 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6482. Min Range: -7.6482
Max Act: 7.0544. Min Act: -0.1700
Data Index: 2293162 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6482. Min Range: -7.6482
Max Act: 7.0232. Min Act: -0.1700
Data Index: 4814861 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.9607. Min Act: -0.1700
Data Index: 8474206 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.8982. Min Act: -0.1700
Data Index: 2145795 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.8982. Min Act: -0.1700
Data Index: 1594652 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.8982. Min Act: -0.1700
Data Index: 1452035 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.8982. Min Act: -0.1700
Data Index: 5494391 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.8982. Min Act: -0.1700
Data Index: 6040073 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19