Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2942 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.1233. Min Range: -13.1233
Max Act: 13.1233. Min Act: -0.1700
Data Index: 6373070 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.1233. Min Range: -13.1233
Max Act: 13.0608. Min Act: -0.1700
Data Index: 6373059 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.1233. Min Range: -13.1233
Max Act: 12.9358. Min Act: -0.1700
Data Index: 6373075 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.1233. Min Range: -13.1233
Max Act: 12.3733. Min Act: -0.1700
Data Index: 5223388 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.1233. Min Range: -13.1233
Max Act: 12.3108. Min Act: -0.1700
Data Index: 2156893 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.1233. Min Range: -13.1233
Max Act: 12.1858. Min Act: -0.1699
Data Index: 7520804 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.1233. Min Range: -13.1233
Max Act: 12.1858. Min Act: -0.1700
Data Index: 2245248 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.1233. Min Range: -13.1233
Max Act: 12.1233. Min Act: -0.1700
Data Index: 5408712 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.1233. Min Range: -13.1233
Max Act: 12.1233. Min Act: -0.1700
Data Index: 5073296 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.1233. Min Range: -13.1233
Max Act: 11.9983. Min Act: -0.1700
Data Index: 5394049 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.1233. Min Range: -13.1233
Max Act: 12.0608. Min Act: -0.1700
Data Index: 996702 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.1233. Min Range: -13.1233
Max Act: 11.9358. Min Act: -0.1700
Data Index: 2235256 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.1233. Min Range: -13.1233
Max Act: 12.0608. Min Act: -0.1700
Data Index: 1778929 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.1233. Min Range: -13.1233
Max Act: 11.9358. Min Act: -0.1700
Data Index: 4696266 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.1233. Min Range: -13.1233
Max Act: 11.8733. Min Act: -0.1700
Data Index: 3037276 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.1233. Min Range: -13.1233
Max Act: 11.8733. Min Act: -0.1700
Data Index: 554558 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.1233. Min Range: -13.1233
Max Act: 11.8733. Min Act: -0.1700
Data Index: 139686 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.1233. Min Range: -13.1233
Max Act: 11.7483. Min Act: -0.1700
Data Index: 2879325 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.1233. Min Range: -13.1233
Max Act: 11.7483. Min Act: -0.1700
Data Index: 4220420 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.1233. Min Range: -13.1233
Max Act: 11.6858. Min Act: -0.1700
Data Index: 1145204 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19