Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 639 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2133. Min Range: -6.2133
Max Act: 6.2133. Min Act: -0.1700
Data Index: 6397606 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.8695. Min Act: -0.1700
Data Index: 5460771 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.7758. Min Act: -0.1700
Data Index: 564735 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.7445. Min Act: -0.1700
Data Index: 5391975 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.7445. Min Act: -0.1700
Data Index: 8225094 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.7133. Min Act: -0.1700
Data Index: 3688871 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.6508. Min Act: -0.1700
Data Index: 4387292 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.6508. Min Act: -0.1700
Data Index: 6201815 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.6195. Min Act: -0.1700
Data Index: 4961962 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.5570. Min Act: -0.1700
Data Index: 8662124 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.5258. Min Act: -0.1700
Data Index: 4967259 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.5258. Min Act: -0.1700
Data Index: 1378608 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.5258. Min Act: -0.1700
Data Index: 5893202 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.5258. Min Act: -0.1700
Data Index: 5627471 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.4945. Min Act: -0.1700
Data Index: 900099 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.4945. Min Act: -0.1700
Data Index: 3870685 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.4633. Min Act: -0.1700
Data Index: 8256616 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.4633. Min Act: -0.1700
Data Index: 1862239 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.4633. Min Act: -0.1700
Data Index: 7665243 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2133. Min Range: -6.2133
Max Act: 5.4633. Min Act: -0.1700
Data Index: 7022394 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19