Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3587 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.4544. Min Act: -0.1700
Data Index: 263096 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3729. Min Act: -0.1700
Data Index: 8459314 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3729. Min Act: -0.1700
Data Index: 252654 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3729. Min Act: -0.1700
Data Index: 6444825 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3565. Min Act: -0.1700
Data Index: 3947112 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3402. Min Act: -0.1700
Data Index: 354406 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3402. Min Act: -0.1700
Data Index: 2043457 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3402. Min Act: -0.1700
Data Index: 3997830 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3402. Min Act: -0.1700
Data Index: 8254226 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3402. Min Act: -0.1700
Data Index: 8558758 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3238. Min Act: -0.1700
Data Index: 3185149 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3402. Min Act: -0.1700
Data Index: 5810528 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3238. Min Act: -0.1700
Data Index: 6949703 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3402. Min Act: -0.1698
Data Index: 4529086 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3073. Min Act: -0.1700
Data Index: 2510596 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3073. Min Act: -0.1700
Data Index: 683121 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3238. Min Act: -0.1700
Data Index: 3499172 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3073. Min Act: -0.1700
Data Index: 1703218 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3238. Min Act: -0.1698
Data Index: 2122931 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4544. Min Range: -2.4544
Max Act: 2.3073. Min Act: -0.1700
Data Index: 7306480 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19