Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 979 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1567. Min Range: -2.1567
Max Act: 2.1567. Min Act: -0.1700
Data Index: 6420463 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1567. Min Range: -2.1567
Max Act: 2.1401. Min Act: -0.1700
Data Index: 401764 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1567. Min Range: -2.1567
Max Act: 2.0899. Min Act: -0.1700
Data Index: 1543952 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1567. Min Range: -2.1567
Max Act: 2.0899. Min Act: -0.1700
Data Index: 6418354 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1567. Min Range: -2.1567
Max Act: 2.0899. Min Act: -0.1700
Data Index: 4480625 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1567. Min Range: -2.1567
Max Act: 2.0563. Min Act: -0.1700
Data Index: 2824876 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1567. Min Range: -2.1567
Max Act: 2.0395. Min Act: -0.1700
Data Index: 2402441 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1567. Min Range: -2.1567
Max Act: 2.0227. Min Act: -0.1700
Data Index: 4480621 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1567. Min Range: -2.1567
Max Act: 2.0395. Min Act: -0.1700
Data Index: 5582863 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1567. Min Range: -2.1567
Max Act: 2.0395. Min Act: -0.1700
Data Index: 8333826 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1567. Min Range: -2.1567
Max Act: 1.9889. Min Act: -0.1700
Data Index: 6036210 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1567. Min Range: -2.1567
Max Act: 2.0058. Min Act: -0.1700
Data Index: 4480626 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1567. Min Range: -2.1567
Max Act: 1.9889. Min Act: -0.1700
Data Index: 4529539 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1567. Min Range: -2.1567
Max Act: 1.9889. Min Act: -0.1700
Data Index: 2171619 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1567. Min Range: -2.1567
Max Act: 1.9889. Min Act: -0.1700
Data Index: 1543950 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1567. Min Range: -2.1567
Max Act: 2.0058. Min Act: -0.1700
Data Index: 1287474 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1567. Min Range: -2.1567
Max Act: 1.9889. Min Act: -0.1700
Data Index: 2788073 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1567. Min Range: -2.1567
Max Act: 1.9889. Min Act: -0.1700
Data Index: 1117664 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1567. Min Range: -2.1567
Max Act: 1.9889. Min Act: -0.1700
Data Index: 4239362 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1567. Min Range: -2.1567
Max Act: 1.9719. Min Act: -0.1700
Data Index: 4480617 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19