Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4659 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.8886. Min Act: -0.1700
Data Index: 6222417 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.8886. Min Act: -0.1700
Data Index: 4770345 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.8574. Min Act: -0.1700
Data Index: 5531008 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.8574. Min Act: -0.1700
Data Index: 413596 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.8261. Min Act: -0.1700
Data Index: 7746164 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.8261. Min Act: -0.1700
Data Index: 7349842 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.8261. Min Act: -0.1700
Data Index: 4807099 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.8261. Min Act: -0.1700
Data Index: 4234453 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7948. Min Act: -0.1700
Data Index: 7540669 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7948. Min Act: -0.1700
Data Index: 4344415 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7948. Min Act: -0.1700
Data Index: 8746998 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7636. Min Act: -0.1700
Data Index: 1449709 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7636. Min Act: -0.1700
Data Index: 4633538 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7636. Min Act: -0.1700
Data Index: 2982276 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7636. Min Act: -0.1700
Data Index: 6972571 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7636. Min Act: -0.1700
Data Index: 7000841 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7636. Min Act: -0.1700
Data Index: 5414777 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7636. Min Act: -0.1700
Data Index: 6608267 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7323. Min Act: -0.1700
Data Index: 2998068 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7636. Min Act: -0.1700
Data Index: 2717550 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19