Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5004 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4224. Min Range: -7.4224
Max Act: 7.4224. Min Act: -0.1700
Data Index: 169380 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4224. Min Range: -7.4224
Max Act: 7.2974. Min Act: -0.1700
Data Index: 160941 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4224. Min Range: -7.4224
Max Act: 7.2037. Min Act: -0.1700
Data Index: 652598 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4224. Min Range: -7.4224
Max Act: 7.2037. Min Act: -0.1700
Data Index: 2887372 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4224. Min Range: -7.4224
Max Act: 7.2037. Min Act: -0.1700
Data Index: 6580720 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4224. Min Range: -7.4224
Max Act: 7.1099. Min Act: -0.1700
Data Index: 8758617 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4224. Min Range: -7.4224
Max Act: 7.0162. Min Act: -0.1700
Data Index: 6148719 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4224. Min Range: -7.4224
Max Act: 6.9537. Min Act: -0.1700
Data Index: 5604673 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4224. Min Range: -7.4224
Max Act: 6.8912. Min Act: -0.1700
Data Index: 3814082 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4224. Min Range: -7.4224
Max Act: 6.8912. Min Act: -0.1700
Data Index: 35917 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4224. Min Range: -7.4224
Max Act: 6.8912. Min Act: -0.1700
Data Index: 3957572 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4224. Min Range: -7.4224
Max Act: 6.8912. Min Act: -0.1700
Data Index: 6163819 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4224. Min Range: -7.4224
Max Act: 6.8599. Min Act: -0.1700
Data Index: 2869912 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4224. Min Range: -7.4224
Max Act: 6.8599. Min Act: -0.1700
Data Index: 4962223 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4224. Min Range: -7.4224
Max Act: 6.8599. Min Act: -0.1700
Data Index: 2574602 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4224. Min Range: -7.4224
Max Act: 6.8599. Min Act: -0.1700
Data Index: 6834432 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4224. Min Range: -7.4224
Max Act: 6.8287. Min Act: -0.1700
Data Index: 885049 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4224. Min Range: -7.4224
Max Act: 6.7662. Min Act: -0.1700
Data Index: 4427138 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4224. Min Range: -7.4224
Max Act: 6.7974. Min Act: -0.1700
Data Index: 3977199 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4224. Min Range: -7.4224
Max Act: 6.7974. Min Act: -0.1700
Data Index: 2215928 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19