Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3781 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6704. Min Range: -9.6704
Max Act: 9.6704. Min Act: -0.1700
Data Index: 2438580 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6704. Min Range: -9.6704
Max Act: 9.4204. Min Act: -0.1700
Data Index: 670508 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6704. Min Range: -9.6704
Max Act: 9.2954. Min Act: -0.1700
Data Index: 4320761 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6704. Min Range: -9.6704
Max Act: 9.2329. Min Act: -0.1700
Data Index: 2506543 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6704. Min Range: -9.6704
Max Act: 9.1704. Min Act: -0.1700
Data Index: 2166194 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6704. Min Range: -9.6704
Max Act: 9.1079. Min Act: -0.1700
Data Index: 7908362 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6704. Min Range: -9.6704
Max Act: 8.9829. Min Act: -0.1700
Data Index: 4696239 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6704. Min Range: -9.6704
Max Act: 8.9829. Min Act: -0.1700
Data Index: 1165708 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6704. Min Range: -9.6704
Max Act: 9.0454. Min Act: -0.1700
Data Index: 7910411 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6704. Min Range: -9.6704
Max Act: 8.9204. Min Act: -0.1700
Data Index: 4296953 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6704. Min Range: -9.6704
Max Act: 8.9829. Min Act: -0.1700
Data Index: 8391761 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6704. Min Range: -9.6704
Max Act: 8.9829. Min Act: -0.1700
Data Index: 7478711 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6704. Min Range: -9.6704
Max Act: 8.9204. Min Act: -0.1700
Data Index: 1051521 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6704. Min Range: -9.6704
Max Act: 8.9204. Min Act: -0.1700
Data Index: 2615915 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6704. Min Range: -9.6704
Max Act: 8.9204. Min Act: -0.1700
Data Index: 1757602 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6704. Min Range: -9.6704
Max Act: 8.9204. Min Act: -0.1700
Data Index: 5527772 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6704. Min Range: -9.6704
Max Act: 8.9204. Min Act: -0.1700
Data Index: 2782211 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6704. Min Range: -9.6704
Max Act: 8.8579. Min Act: -0.1700
Data Index: 4463633 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6704. Min Range: -9.6704
Max Act: 8.8579. Min Act: -0.1700
Data Index: 7869690 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6704. Min Range: -9.6704
Max Act: 8.8579. Min Act: -0.1700
Data Index: 5604118 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19