Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2105 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.5525. Min Act: -0.1700
Data Index: 486634 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.5349. Min Act: -0.1700
Data Index: 3369962 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.5174. Min Act: -0.1700
Data Index: 232260 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.5174. Min Act: -0.1700
Data Index: 366098 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.4823. Min Act: -0.1700
Data Index: 4209010 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.4999. Min Act: -0.1700
Data Index: 1325475 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.4999. Min Act: -0.1700
Data Index: 8631965 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.4823. Min Act: -0.1700
Data Index: 6152130 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.4823. Min Act: -0.1700
Data Index: 2338110 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.4823. Min Act: -0.1700
Data Index: 4999673 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.4823. Min Act: -0.1699
Data Index: 1774662 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.4823. Min Act: -0.1700
Data Index: 3217909 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.4471. Min Act: -0.1700
Data Index: 8785097 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.4647. Min Act: -0.1700
Data Index: 7535347 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.4647. Min Act: -0.1700
Data Index: 41823 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.4471. Min Act: -0.1700
Data Index: 3280178 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.4471. Min Act: -0.1700
Data Index: 3908015 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.4471. Min Act: -0.1700
Data Index: 6435603 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.4471. Min Act: -0.1700
Data Index: 6445668 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5525. Min Range: -1.5525
Max Act: 1.4471. Min Act: -0.1700
Data Index: 3911784 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19