Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1321 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.6143. Min Act: -0.1700
Data Index: 1714896 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.3956. Min Act: -0.1700
Data Index: 4816438 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.3956. Min Act: -0.1700
Data Index: 8687513 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.3643. Min Act: -0.1700
Data Index: 8567749 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.2706. Min Act: -0.1700
Data Index: 5126766 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.2706. Min Act: -0.1700
Data Index: 1842397 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.2706. Min Act: -0.1700
Data Index: 7227983 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.2706. Min Act: -0.1700
Data Index: 1531466 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.2706. Min Act: -0.1700
Data Index: 3431350 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.2393. Min Act: -0.1700
Data Index: 7576958 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.2081. Min Act: -0.1700
Data Index: 8800431 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.2081. Min Act: -0.1700
Data Index: 5527606 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.1768. Min Act: -0.1700
Data Index: 6848608 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.2081. Min Act: -0.1700
Data Index: 3762403 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.1768. Min Act: -0.1700
Data Index: 3022593 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.1768. Min Act: -0.1700
Data Index: 364586 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.1455. Min Act: -0.1700
Data Index: 1633997 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.1455. Min Act: -0.1700
Data Index: 4370344 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.1455. Min Act: -0.1700
Data Index: 7681108 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6143. Min Range: -4.6143
Max Act: 4.1455. Min Act: -0.1700
Data Index: 7525714 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19