Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.3634. Min Act: -0.1700
Data Index: 2344758 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.2648. Min Act: -0.1700
Data Index: 3394117 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.2648. Min Act: -0.1700
Data Index: 5973502 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.2483. Min Act: -0.1700
Data Index: 2136908 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.2318. Min Act: -0.1700
Data Index: 7371292 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.2483. Min Act: -0.1700
Data Index: 3554783 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.2483. Min Act: -0.1700
Data Index: 7218798 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.2318. Min Act: -0.1700
Data Index: 2344757 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.2318. Min Act: -0.1700
Data Index: 3740364 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.2152. Min Act: -0.1700
Data Index: 2160086 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.1654. Min Act: -0.1700
Data Index: 1279304 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.1820. Min Act: -0.1700
Data Index: 6234982 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.1820. Min Act: -0.1700
Data Index: 1730506 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.1654. Min Act: -0.1700
Data Index: 8473460 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.1487. Min Act: -0.1700
Data Index: 8014974 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.1487. Min Act: -0.1700
Data Index: 4798542 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.1654. Min Act: -0.1700
Data Index: 4537087 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.1487. Min Act: -0.1700
Data Index: 8612272 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.1487. Min Act: -0.1700
Data Index: 3554070 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3634. Min Range: -2.3634
Max Act: 2.1320. Min Act: -0.1700
Data Index: 4258687 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19