Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2172 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.9944. Min Act: -0.1700
Data Index: 2110880 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.8381. Min Act: -0.1700
Data Index: 8169807 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.8381. Min Act: -0.1700
Data Index: 7976491 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.8381. Min Act: -0.1700
Data Index: 2704303 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.8381. Min Act: -0.1700
Data Index: 7312145 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.8381. Min Act: -0.1700
Data Index: 3710640 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.7755. Min Act: -0.1700
Data Index: 3745196 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.8068. Min Act: -0.1700
Data Index: 6274929 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.7755. Min Act: -0.1700
Data Index: 3970548 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.7755. Min Act: -0.1700
Data Index: 1783255 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.8068. Min Act: -0.1700
Data Index: 4826361 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.7442. Min Act: -0.1700
Data Index: 1595110 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.7442. Min Act: -0.1700
Data Index: 2484144 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.7442. Min Act: -0.1700
Data Index: 6752917 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.7442. Min Act: -0.1700
Data Index: 1869251 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.7442. Min Act: -0.1700
Data Index: 2436783 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.7442. Min Act: -0.1700
Data Index: 4264779 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.7442. Min Act: -0.1700
Data Index: 4340108 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.7130. Min Act: -0.1700
Data Index: 3507529 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9944. Min Range: -3.9944
Max Act: 3.7130. Min Act: -0.1700
Data Index: 5351944 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19