Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3042 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0612. Min Range: -5.0612
Max Act: 5.0612. Min Act: -0.1700
Data Index: 4860421 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.9987. Min Act: -0.1700
Data Index: 5436564 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.9362. Min Act: -0.1700
Data Index: 4193665 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.9049. Min Act: -0.1700
Data Index: 1388922 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.9362. Min Act: -0.1700
Data Index: 247148 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.9049. Min Act: -0.1700
Data Index: 6990035 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.9049. Min Act: -0.1700
Data Index: 4375873 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.9049. Min Act: -0.1700
Data Index: 6604398 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.9049. Min Act: -0.1700
Data Index: 728819 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.9049. Min Act: -0.1700
Data Index: 2342318 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.8737. Min Act: -0.1700
Data Index: 2442738 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.8737. Min Act: -0.1700
Data Index: 6344763 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.9049. Min Act: -0.1699
Data Index: 2659174 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.8737. Min Act: -0.1700
Data Index: 477524 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.9049. Min Act: -0.1700
Data Index: 4860417 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.8424. Min Act: -0.1700
Data Index: 1609347 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.8424. Min Act: -0.1700
Data Index: 5851780 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.8424. Min Act: -0.1700
Data Index: 6096908 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.8112. Min Act: -0.1700
Data Index: 4528386 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.8424. Min Act: -0.1700
Data Index: 4687070 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19