Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1120 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.8710. Min Act: -0.1700
Data Index: 2860977 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.7772. Min Act: -0.1700
Data Index: 3444789 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.6522. Min Act: -0.1700
Data Index: 4474608 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.6210. Min Act: -0.1700
Data Index: 998126 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.6210. Min Act: -0.1700
Data Index: 1520265 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.5585. Min Act: -0.1700
Data Index: 5546099 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.5897. Min Act: -0.1700
Data Index: 3156439 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.5272. Min Act: -0.1700
Data Index: 4378764 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.5585. Min Act: -0.1700
Data Index: 8422540 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.5272. Min Act: -0.1700
Data Index: 2423501 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4960. Min Act: -0.1700
Data Index: 565680 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.5272. Min Act: -0.1700
Data Index: 4590324 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4960. Min Act: -0.1700
Data Index: 8099664 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4647. Min Act: -0.1700
Data Index: 6052749 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4647. Min Act: -0.1700
Data Index: 2043793 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4647. Min Act: -0.1700
Data Index: 6549512 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4960. Min Act: -0.1700
Data Index: 5305585 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4647. Min Act: -0.1700
Data Index: 542544 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4647. Min Act: -0.1700
Data Index: 8379052 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4647. Min Act: -0.1700
Data Index: 3187039 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19