Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2649 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.6765. Min Act: -0.1700
Data Index: 6720133 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.6765. Min Act: -0.1700
Data Index: 7604644 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.6765. Min Act: -0.1700
Data Index: 3859381 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.5982. Min Act: -0.1700
Data Index: 4437393 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.5200. Min Act: -0.1700
Data Index: 7485866 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.5200. Min Act: -0.1700
Data Index: 3346900 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4886. Min Act: -0.1700
Data Index: 165866 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.5043. Min Act: -0.1700
Data Index: 4745852 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.5043. Min Act: -0.1700
Data Index: 3180757 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4886. Min Act: -0.1700
Data Index: 4444246 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.5043. Min Act: -0.1700
Data Index: 8323459 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.5043. Min Act: -0.1700
Data Index: 6849212 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4573. Min Act: -0.1700
Data Index: 2075039 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4730. Min Act: -0.1700
Data Index: 2509805 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4573. Min Act: -0.1700
Data Index: 1961638 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4730. Min Act: -0.1700
Data Index: 4700459 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4573. Min Act: -0.1700
Data Index: 4923836 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4260. Min Act: -0.1700
Data Index: 2261177 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4416. Min Act: -0.1700
Data Index: 5468137 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4573. Min Act: -0.1700
Data Index: 2490209 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19