Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2600 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0574. Min Range: -4.0574
Max Act: 4.0574. Min Act: -0.1700
Data Index: 4229594 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9949. Min Act: -0.1700
Data Index: 6397332 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9949. Min Act: -0.1700
Data Index: 7963460 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9636. Min Act: -0.1700
Data Index: 1137674 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9636. Min Act: -0.1700
Data Index: 8239117 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9636. Min Act: -0.1700
Data Index: 700756 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9324. Min Act: -0.1700
Data Index: 2623741 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9324. Min Act: -0.1700
Data Index: 6600085 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9324. Min Act: -0.1700
Data Index: 6600082 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.8698. Min Act: -0.1700
Data Index: 3175965 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.8698. Min Act: -0.1700
Data Index: 6720748 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.8698. Min Act: -0.1700
Data Index: 8821554 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.8386. Min Act: -0.1700
Data Index: 4229587 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.8698. Min Act: -0.1700
Data Index: 4182060 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.8698. Min Act: -0.1700
Data Index: 3894286 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.8386. Min Act: -0.1700
Data Index: 71661 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.8073. Min Act: -0.1700
Data Index: 4117020 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.8073. Min Act: -0.1700
Data Index: 7369013 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.8073. Min Act: -0.1700
Data Index: 3610831 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.7760. Min Act: -0.1700
Data Index: 2637233 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19