Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1928 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3806. Min Range: -9.3806
Max Act: 9.3806. Min Act: -0.1700
Data Index: 7950872 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3806. Min Range: -9.3806
Max Act: 9.1931. Min Act: -0.1700
Data Index: 7613024 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3806. Min Range: -9.3806
Max Act: 9.1931. Min Act: -0.1700
Data Index: 2349701 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3806. Min Range: -9.3806
Max Act: 9.1931. Min Act: -0.1700
Data Index: 7072216 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3806. Min Range: -9.3806
Max Act: 9.1306. Min Act: -0.1700
Data Index: 4002853 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3806. Min Range: -9.3806
Max Act: 9.0681. Min Act: -0.1700
Data Index: 7700040 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3806. Min Range: -9.3806
Max Act: 9.0681. Min Act: -0.1700
Data Index: 1026684 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3806. Min Range: -9.3806
Max Act: 9.0681. Min Act: -0.1700
Data Index: 1577731 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3806. Min Range: -9.3806
Max Act: 9.0056. Min Act: -0.1700
Data Index: 4646603 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3806. Min Range: -9.3806
Max Act: 9.0056. Min Act: -0.1700
Data Index: 8519890 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3806. Min Range: -9.3806
Max Act: 8.9431. Min Act: -0.1700
Data Index: 470355 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3806. Min Range: -9.3806
Max Act: 8.8806. Min Act: -0.1700
Data Index: 7860372 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3806. Min Range: -9.3806
Max Act: 8.8806. Min Act: -0.1700
Data Index: 3811158 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3806. Min Range: -9.3806
Max Act: 8.8806. Min Act: -0.1700
Data Index: 6813597 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3806. Min Range: -9.3806
Max Act: 8.8181. Min Act: -0.1700
Data Index: 3752059 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3806. Min Range: -9.3806
Max Act: 8.8181. Min Act: -0.1700
Data Index: 8695382 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3806. Min Range: -9.3806
Max Act: 8.8181. Min Act: -0.1700
Data Index: 6131155 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3806. Min Range: -9.3806
Max Act: 8.8181. Min Act: -0.1700
Data Index: 3555956 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3806. Min Range: -9.3806
Max Act: 8.7556. Min Act: -0.1700
Data Index: 174295 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3806. Min Range: -9.3806
Max Act: 8.7556. Min Act: -0.1700
Data Index: 7507652 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19