Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3517 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.9741. Min Act: -0.1700
Data Index: 2052905 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0054. Min Range: -5.0054
Max Act: 5.0054. Min Act: -0.1700
Data Index: 4266346 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.9429. Min Act: -0.1700
Data Index: 5337727 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.8804. Min Act: -0.1700
Data Index: 5721478 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.8804. Min Act: -0.1700
Data Index: 1144358 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.8179. Min Act: -0.1700
Data Index: 6695521 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.8491. Min Act: -0.1700
Data Index: 6634313 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.7554. Min Act: -0.1700
Data Index: 5114695 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.7554. Min Act: -0.1700
Data Index: 7917377 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.6929. Min Act: -0.1700
Data Index: 7619375 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.6929. Min Act: -0.1700
Data Index: 7045747 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.6616. Min Act: -0.1700
Data Index: 7793673 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.6304. Min Act: -0.1700
Data Index: 6406481 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.6304. Min Act: -0.1700
Data Index: 3332200 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.5991. Min Act: -0.1700
Data Index: 3180553 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.5991. Min Act: -0.1700
Data Index: 381630 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.5991. Min Act: -0.1700
Data Index: 2977254 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.6304. Min Act: -0.1700
Data Index: 554949 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.5991. Min Act: -0.1700
Data Index: 2280058 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0054. Min Range: -5.0054
Max Act: 4.5991. Min Act: -0.1700
Data Index: 8717305 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19