Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3730 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1730. Min Range: -4.1730
Max Act: 4.1730. Min Act: -0.1700
Data Index: 5523319 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.8291. Min Act: -0.1700
Data Index: 8244230 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.9542. Min Act: -0.1700
Data Index: 5414400 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.9854. Min Act: -0.1700
Data Index: 8263877 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.9542. Min Act: -0.1700
Data Index: 4571944 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.9542. Min Act: -0.1700
Data Index: 7419140 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.9229. Min Act: -0.1700
Data Index: 1993578 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.9229. Min Act: -0.1700
Data Index: 8581152 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.9229. Min Act: -0.1700
Data Index: 2526278 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.8917. Min Act: -0.1700
Data Index: 8680766 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.9229. Min Act: -0.1700
Data Index: 7534101 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.8917. Min Act: -0.1700
Data Index: 935196 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.8917. Min Act: -0.1700
Data Index: 7801865 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.8604. Min Act: -0.1700
Data Index: 2033616 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.8917. Min Act: -0.1700
Data Index: 7023034 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.8917. Min Act: -0.1700
Data Index: 7954494 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.8604. Min Act: -0.1700
Data Index: 4171559 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.8917. Min Act: -0.1700
Data Index: 2392697 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.8604. Min Act: -0.1700
Data Index: 4249022 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1730. Min Range: -4.1730
Max Act: 3.8604. Min Act: -0.1700
Data Index: 6310497 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19