Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 671 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3338. Min Range: -6.3338
Max Act: 6.3338. Min Act: -0.1700
Data Index: 5996175 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3338. Min Range: -6.3338
Max Act: 6.2401. Min Act: -0.1700
Data Index: 1513323 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3338. Min Range: -6.3338
Max Act: 6.2088. Min Act: -0.1700
Data Index: 6530458 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3338. Min Range: -6.3338
Max Act: 6.2088. Min Act: -0.1700
Data Index: 3264223 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3338. Min Range: -6.3338
Max Act: 6.1151. Min Act: -0.1700
Data Index: 517537 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3338. Min Range: -6.3338
Max Act: 6.0838. Min Act: -0.1700
Data Index: 6300524 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3338. Min Range: -6.3338
Max Act: 6.0213. Min Act: -0.1700
Data Index: 2242975 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3338. Min Range: -6.3338
Max Act: 5.8963. Min Act: -0.1700
Data Index: 138668 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3338. Min Range: -6.3338
Max Act: 5.8963. Min Act: -0.1700
Data Index: 1995025 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3338. Min Range: -6.3338
Max Act: 5.9276. Min Act: -0.1700
Data Index: 6097336 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3338. Min Range: -6.3338
Max Act: 5.9276. Min Act: -0.1700
Data Index: 1845641 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3338. Min Range: -6.3338
Max Act: 5.8963. Min Act: -0.1700
Data Index: 3202250 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3338. Min Range: -6.3338
Max Act: 5.8963. Min Act: -0.1700
Data Index: 2015538 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3338. Min Range: -6.3338
Max Act: 5.8963. Min Act: -0.1700
Data Index: 5970140 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3338. Min Range: -6.3338
Max Act: 5.8963. Min Act: -0.1700
Data Index: 8359029 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3338. Min Range: -6.3338
Max Act: 5.8338. Min Act: -0.1700
Data Index: 8384489 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3338. Min Range: -6.3338
Max Act: 5.8963. Min Act: -0.1700
Data Index: 1757989 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3338. Min Range: -6.3338
Max Act: 5.8651. Min Act: -0.1700
Data Index: 5638210 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3338. Min Range: -6.3338
Max Act: 5.8651. Min Act: -0.1700
Data Index: 4292594 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3338. Min Range: -6.3338
Max Act: 5.8338. Min Act: -0.1700
Data Index: 955939 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19