Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.9737. Min Act: -0.1700
Data Index: 352184 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.6612. Min Act: -0.1700
Data Index: 3682238 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.6612. Min Act: -0.1700
Data Index: 6342649 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.6300. Min Act: -0.1700
Data Index: 3472019 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.6300. Min Act: -0.1700
Data Index: 154700 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.5675. Min Act: -0.1700
Data Index: 2674702 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.5362. Min Act: -0.1700
Data Index: 8542369 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.5362. Min Act: -0.1700
Data Index: 1316247 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.4737. Min Act: -0.1700
Data Index: 2716441 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.4112. Min Act: -0.1700
Data Index: 4756165 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.4425. Min Act: -0.1700
Data Index: 7362824 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.4737. Min Act: -0.1700
Data Index: 4212117 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.4112. Min Act: -0.1700
Data Index: 5436367 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.3800. Min Act: -0.1700
Data Index: 687630 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.4112. Min Act: -0.1700
Data Index: 3178489 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.4112. Min Act: -0.1700
Data Index: 7424990 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.4112. Min Act: -0.1700
Data Index: 5364111 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.3800. Min Act: -0.1700
Data Index: 3725127 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.4112. Min Act: -0.1700
Data Index: 1699153 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9737. Min Range: -5.9737
Max Act: 5.4425. Min Act: -0.1700
Data Index: 2688755 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19