Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5231 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.2099. Min Act: -0.1700
Data Index: 27033 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1786. Min Act: -0.1700
Data Index: 3616440 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1473. Min Act: -0.1700
Data Index: 4897884 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1473. Min Act: -0.1700
Data Index: 1343405 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1161. Min Act: -0.1700
Data Index: 3196315 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.0848. Min Act: -0.1700
Data Index: 2705937 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1161. Min Act: -0.1700
Data Index: 5192781 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1161. Min Act: -0.1700
Data Index: 1663289 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.0848. Min Act: -0.1700
Data Index: 598609 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.0536. Min Act: -0.1700
Data Index: 4510056 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.0223. Min Act: -0.1700
Data Index: 6105843 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.0223. Min Act: -0.1700
Data Index: 314003 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.0223. Min Act: -0.1700
Data Index: 6196418 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.0223. Min Act: -0.1700
Data Index: 4650445 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2099. Min Range: -4.2099
Max Act: 3.9911. Min Act: -0.1700
Data Index: 6604701 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2099. Min Range: -4.2099
Max Act: 3.9911. Min Act: -0.1700
Data Index: 6962846 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2099. Min Range: -4.2099
Max Act: 3.9598. Min Act: -0.1700
Data Index: 161664 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2099. Min Range: -4.2099
Max Act: 3.9911. Min Act: -0.1700
Data Index: 6105845 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2099. Min Range: -4.2099
Max Act: 3.9598. Min Act: -0.1700
Data Index: 1565182 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2099. Min Range: -4.2099
Max Act: 3.9598. Min Act: -0.1700
Data Index: 2206703 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19