Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2738 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.0942. Min Act: -0.1700
Data Index: 3327969 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.1879. Min Act: -0.1700
Data Index: 3785760 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.1254. Min Act: -0.1700
Data Index: 5927223 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.1254. Min Act: -0.1700
Data Index: 1455157 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.0629. Min Act: -0.1700
Data Index: 8164550 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.1254. Min Act: -0.1700
Data Index: 3805251 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.0942. Min Act: -0.1700
Data Index: 7498600 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.1879. Min Act: -0.1700
Data Index: 2952076 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.0317. Min Act: -0.1700
Data Index: 4774128 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.0942. Min Act: -0.1700
Data Index: 8779525 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.0317. Min Act: -0.1700
Data Index: 6321920 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.0629. Min Act: -0.1700
Data Index: 3355941 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.0942. Min Act: -0.1700
Data Index: 3189446 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1879. Min Range: -8.1879
Max Act: 7.9692. Min Act: -0.1700
Data Index: 3381811 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.0004. Min Act: -0.1700
Data Index: 8763309 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.0317. Min Act: -0.1700
Data Index: 1189885 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.0004. Min Act: -0.1700
Data Index: 6959463 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.0629. Min Act: -0.1700
Data Index: 1836660 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.0317. Min Act: -0.1700
Data Index: 4544716 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1879. Min Range: -8.1879
Max Act: 8.0004. Min Act: -0.1700
Data Index: 7143708 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19