Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3069 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.3626. Min Act: -0.1700
Data Index: 8171736 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.2970. Min Act: -0.1700
Data Index: 6378786 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.2640. Min Act: -0.1700
Data Index: 1631311 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.2805. Min Act: -0.1700
Data Index: 5372876 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.2475. Min Act: -0.1700
Data Index: 4550149 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.2475. Min Act: -0.1700
Data Index: 2762165 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.2310. Min Act: -0.1700
Data Index: 7731243 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.2144. Min Act: -0.1700
Data Index: 7145298 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.1978. Min Act: -0.1700
Data Index: 3493837 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.1978. Min Act: -0.1700
Data Index: 7570174 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.1812. Min Act: -0.1700
Data Index: 3912304 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.1646. Min Act: -0.1700
Data Index: 1888444 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.1646. Min Act: -0.1700
Data Index: 5575143 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.1145. Min Act: -0.1700
Data Index: 4541861 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.1145. Min Act: -0.1700
Data Index: 8418980 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.1145. Min Act: -0.1700
Data Index: 5074011 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.1479. Min Act: -0.1700
Data Index: 85276 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.1145. Min Act: -0.1700
Data Index: 6476065 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.1312. Min Act: -0.1700
Data Index: 3650582 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3626. Min Range: -2.3626
Max Act: 2.1312. Min Act: -0.1700
Data Index: 4838900 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19