Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4326 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0360. Min Range: -3.0360
Max Act: 3.0360. Min Act: -0.1700
Data Index: 4656858 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0360. Min Range: -3.0360
Max Act: 3.0202. Min Act: -0.1700
Data Index: 6977395 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.9570. Min Act: -0.1700
Data Index: 7135154 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.9253. Min Act: -0.1700
Data Index: 5902198 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.9412. Min Act: -0.1700
Data Index: 2040348 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.9095. Min Act: -0.1700
Data Index: 1064851 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.9095. Min Act: -0.1700
Data Index: 8360083 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8777. Min Act: -0.1700
Data Index: 5235680 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8619. Min Act: -0.1700
Data Index: 4463794 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8777. Min Act: -0.1700
Data Index: 4318383 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8777. Min Act: -0.1700
Data Index: 1647320 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8460. Min Act: -0.1700
Data Index: 4154958 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8777. Min Act: -0.1700
Data Index: 7341047 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8460. Min Act: -0.1700
Data Index: 4347981 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8460. Min Act: -0.1700
Data Index: 7386709 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8301. Min Act: -0.1700
Data Index: 100781 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8460. Min Act: -0.1700
Data Index: 6615948 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8460. Min Act: -0.1700
Data Index: 1447450 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8142. Min Act: -0.1700
Data Index: 4773882 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8142. Min Act: -0.1700
Data Index: 549111 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19