Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2947. Min Range: -8.2947
Max Act: 8.2947. Min Act: -0.1700
Data Index: 6177384 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2947. Min Range: -8.2947
Max Act: 8.2322. Min Act: -0.1700
Data Index: 1004639 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2947. Min Range: -8.2947
Max Act: 8.1697. Min Act: -0.1700
Data Index: 7260230 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2947. Min Range: -8.2947
Max Act: 7.9822. Min Act: -0.1700
Data Index: 2345429 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2947. Min Range: -8.2947
Max Act: 7.9822. Min Act: -0.1700
Data Index: 895375 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2947. Min Range: -8.2947
Max Act: 7.9822. Min Act: -0.1700
Data Index: 1644004 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2947. Min Range: -8.2947
Max Act: 7.9822. Min Act: -0.1700
Data Index: 3968026 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2947. Min Range: -8.2947
Max Act: 7.9822. Min Act: -0.1700
Data Index: 8443988 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2947. Min Range: -8.2947
Max Act: 7.9822. Min Act: -0.1700
Data Index: 7899222 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2947. Min Range: -8.2947
Max Act: 7.9197. Min Act: -0.1700
Data Index: 6965505 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2947. Min Range: -8.2947
Max Act: 7.9197. Min Act: -0.1700
Data Index: 1717767 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2947. Min Range: -8.2947
Max Act: 7.9197. Min Act: -0.1700
Data Index: 6038587 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2947. Min Range: -8.2947
Max Act: 7.9197. Min Act: -0.1700
Data Index: 4099093 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2947. Min Range: -8.2947
Max Act: 7.9197. Min Act: -0.1700
Data Index: 2324023 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2947. Min Range: -8.2947
Max Act: 7.8885. Min Act: -0.1700
Data Index: 7786979 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2947. Min Range: -8.2947
Max Act: 7.8885. Min Act: -0.1700
Data Index: 7283004 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2947. Min Range: -8.2947
Max Act: 7.8885. Min Act: -0.1700
Data Index: 8546509 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2947. Min Range: -8.2947
Max Act: 7.8885. Min Act: -0.1700
Data Index: 1422116 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2947. Min Range: -8.2947
Max Act: 7.8572. Min Act: -0.1700
Data Index: 6504598 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2947. Min Range: -8.2947
Max Act: 7.8572. Min Act: -0.1700
Data Index: 3995075 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19