Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.7146. Min Act: -0.1700
Data Index: 5022523 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.6521. Min Act: -0.1700
Data Index: 28784 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.5271. Min Act: -0.1700
Data Index: 6248313 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.5271. Min Act: -0.1700
Data Index: 2072271 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.4646. Min Act: -0.1700
Data Index: 7096624 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.5271. Min Act: -0.1700
Data Index: 4233964 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.4646. Min Act: -0.1700
Data Index: 3683905 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.4646. Min Act: -0.1700
Data Index: 8311078 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.3396. Min Act: -0.1700
Data Index: 1282768 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.3396. Min Act: -0.1700
Data Index: 8062299 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.3396. Min Act: -0.1700
Data Index: 2501392 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.2771. Min Act: -0.1700
Data Index: 3806381 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.2146. Min Act: -0.1700
Data Index: 5005567 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.2146. Min Act: -0.1700
Data Index: 62047 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.1521. Min Act: -0.1700
Data Index: 2318333 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.1521. Min Act: -0.1700
Data Index: 3178386 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.1521. Min Act: -0.1700
Data Index: 7069567 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.1521. Min Act: -0.1700
Data Index: 7863990 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.0896. Min Act: -0.1700
Data Index: 7012683 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7146. Min Range: -8.7146
Max Act: 8.0896. Min Act: -0.1700
Data Index: 2667620 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19