Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 708 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0711. Min Range: -4.0711
Max Act: 4.0711. Min Act: -0.1700
Data Index: 2119407 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0711. Min Range: -4.0711
Max Act: 4.0711. Min Act: -0.1700
Data Index: 5979848 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0711. Min Range: -4.0711
Max Act: 4.0085. Min Act: -0.1700
Data Index: 2301788 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0711. Min Range: -4.0711
Max Act: 4.0085. Min Act: -0.1700
Data Index: 7296676 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0711. Min Range: -4.0711
Max Act: 4.0085. Min Act: -0.1700
Data Index: 1014836 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0711. Min Range: -4.0711
Max Act: 4.0085. Min Act: -0.1700
Data Index: 3816527 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0711. Min Range: -4.0711
Max Act: 4.0085. Min Act: -0.1700
Data Index: 6358161 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9773. Min Act: -0.1700
Data Index: 8217008 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9773. Min Act: -0.1700
Data Index: 4950582 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9460. Min Act: -0.1700
Data Index: 2253268 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9773. Min Act: -0.1700
Data Index: 4969193 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9304. Min Act: -0.1700
Data Index: 8655150 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9304. Min Act: -0.1700
Data Index: 5105001 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9304. Min Act: -0.1700
Data Index: 4649242 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9304. Min Act: -0.1700
Data Index: 5159328 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9304. Min Act: -0.1700
Data Index: 3524406 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9304. Min Act: -0.1700
Data Index: 212447 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.8991. Min Act: -0.1700
Data Index: 694928 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.8991. Min Act: -0.1700
Data Index: 7950507 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9148. Min Act: -0.1700
Data Index: 8051607 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19