Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.5746. Min Act: -0.1700
Data Index: 5149034 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.5434. Min Act: -0.1700
Data Index: 3452660 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.3871. Min Act: -0.1700
Data Index: 1740598 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.3246. Min Act: -0.1700
Data Index: 3234179 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.3246. Min Act: -0.1700
Data Index: 6827075 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.2934. Min Act: -0.1700
Data Index: 5537019 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.2934. Min Act: -0.1700
Data Index: 5486169 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.2621. Min Act: -0.1700
Data Index: 1899797 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.2621. Min Act: -0.1700
Data Index: 1678699 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.2621. Min Act: -0.1700
Data Index: 4219086 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.2309. Min Act: -0.1700
Data Index: 2412791 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.2309. Min Act: -0.1700
Data Index: 3932271 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.1996. Min Act: -0.1700
Data Index: 869119 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.1684. Min Act: -0.1700
Data Index: 57241 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.1996. Min Act: -0.1700
Data Index: 7105317 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.1996. Min Act: -0.1700
Data Index: 5974169 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.1371. Min Act: -0.1700
Data Index: 5029078 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.1371. Min Act: -0.1700
Data Index: 8784198 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.1371. Min Act: -0.1700
Data Index: 8566468 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5746. Min Range: -7.5746
Max Act: 7.1371. Min Act: -0.1700
Data Index: 905722 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19