Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1924 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2778. Min Range: -4.2778
Max Act: 4.2778. Min Act: -0.1700
Data Index: 5966328 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2778. Min Range: -4.2778
Max Act: 4.1840. Min Act: -0.1700
Data Index: 2986068 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2778. Min Range: -4.2778
Max Act: 4.1528. Min Act: -0.1700
Data Index: 753157 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2778. Min Range: -4.2778
Max Act: 4.1528. Min Act: -0.1700
Data Index: 3660864 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2778. Min Range: -4.2778
Max Act: 4.1528. Min Act: -0.1700
Data Index: 6344830 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2778. Min Range: -4.2778
Max Act: 4.1215. Min Act: -0.1700
Data Index: 8782313 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2778. Min Range: -4.2778
Max Act: 4.1215. Min Act: -0.1700
Data Index: 7554887 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2778. Min Range: -4.2778
Max Act: 4.0903. Min Act: -0.1700
Data Index: 1590707 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2778. Min Range: -4.2778
Max Act: 4.0590. Min Act: -0.1700
Data Index: 8547651 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2778. Min Range: -4.2778
Max Act: 4.0903. Min Act: -0.1700
Data Index: 997336 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2778. Min Range: -4.2778
Max Act: 4.0903. Min Act: -0.1700
Data Index: 7218877 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2778. Min Range: -4.2778
Max Act: 4.0903. Min Act: -0.1700
Data Index: 3484797 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2778. Min Range: -4.2778
Max Act: 4.0903. Min Act: -0.1700
Data Index: 157257 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2778. Min Range: -4.2778
Max Act: 4.0590. Min Act: -0.1700
Data Index: 6352355 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2778. Min Range: -4.2778
Max Act: 4.0590. Min Act: -0.1700
Data Index: 4141587 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2778. Min Range: -4.2778
Max Act: 4.0590. Min Act: -0.1700
Data Index: 606108 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2778. Min Range: -4.2778
Max Act: 4.0590. Min Act: -0.1700
Data Index: 2779157 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2778. Min Range: -4.2778
Max Act: 3.9965. Min Act: -0.1700
Data Index: 2959710 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2778. Min Range: -4.2778
Max Act: 4.0277. Min Act: -0.1700
Data Index: 3709955 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2778. Min Range: -4.2778
Max Act: 3.9965. Min Act: -0.1700
Data Index: 4487081 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19