Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3824 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.9675. Min Act: -0.1700
Data Index: 4722978 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.8248. Min Act: -0.1700
Data Index: 8785075 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.8089. Min Act: -0.1700
Data Index: 8182470 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.8089. Min Act: -0.1700
Data Index: 936661 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.7929. Min Act: -0.1700
Data Index: 1310652 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.7929. Min Act: -0.1700
Data Index: 8127581 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.7770. Min Act: -0.1700
Data Index: 424664 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.7770. Min Act: -0.1700
Data Index: 3733327 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.7451. Min Act: -0.1700
Data Index: 4191593 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.7451. Min Act: -0.1700
Data Index: 424666 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.7451. Min Act: -0.1700
Data Index: 8146869 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.7451. Min Act: -0.1700
Data Index: 1122221 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.7291. Min Act: -0.1700
Data Index: 8127589 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.7291. Min Act: -0.1700
Data Index: 3732868 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.7131. Min Act: -0.1700
Data Index: 7498134 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.7131. Min Act: -0.1700
Data Index: 8462498 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.6971. Min Act: -0.1700
Data Index: 4592899 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.7131. Min Act: -0.1700
Data Index: 5008515 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.6811. Min Act: -0.1700
Data Index: 6858525 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9675. Min Range: -2.9675
Max Act: 2.6811. Min Act: -0.1700
Data Index: 6425965 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19