Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2475 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2549. Min Range: -3.2549
Max Act: 3.2549. Min Act: -0.1700
Data Index: 7844580 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2549. Min Range: -3.2549
Max Act: 3.2392. Min Act: -0.1700
Data Index: 6556594 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2549. Min Range: -3.2549
Max Act: 3.2235. Min Act: -0.1700
Data Index: 1632261 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2549. Min Range: -3.2549
Max Act: 3.1920. Min Act: -0.1700
Data Index: 7019605 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2549. Min Range: -3.2549
Max Act: 3.1133. Min Act: -0.1700
Data Index: 8749972 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2549. Min Range: -3.2549
Max Act: 3.0818. Min Act: -0.1700
Data Index: 8102070 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2549. Min Range: -3.2549
Max Act: 3.0818. Min Act: -0.1700
Data Index: 2129040 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2549. Min Range: -3.2549
Max Act: 3.0502. Min Act: -0.1700
Data Index: 818417 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2549. Min Range: -3.2549
Max Act: 3.0502. Min Act: -0.1700
Data Index: 710498 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2549. Min Range: -3.2549
Max Act: 3.0502. Min Act: -0.1700
Data Index: 2494229 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2549. Min Range: -3.2549
Max Act: 3.0660. Min Act: -0.1700
Data Index: 6079450 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2549. Min Range: -3.2549
Max Act: 3.0344. Min Act: -0.1700
Data Index: 4885872 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2549. Min Range: -3.2549
Max Act: 3.0344. Min Act: -0.1700
Data Index: 8460699 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2549. Min Range: -3.2549
Max Act: 3.0187. Min Act: -0.1700
Data Index: 3265578 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2549. Min Range: -3.2549
Max Act: 3.0344. Min Act: -0.1700
Data Index: 5227503 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2549. Min Range: -3.2549
Max Act: 2.9870. Min Act: -0.1700
Data Index: 5235748 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2549. Min Range: -3.2549
Max Act: 3.0029. Min Act: -0.1700
Data Index: 4988005 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2549. Min Range: -3.2549
Max Act: 3.0187. Min Act: -0.1700
Data Index: 6397071 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2549. Min Range: -3.2549
Max Act: 3.0029. Min Act: -0.1700
Data Index: 6380049 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2549. Min Range: -3.2549
Max Act: 2.9870. Min Act: -0.1700
Data Index: 4877878 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19