Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4859 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.4216. Min Act: -0.1700
Data Index: 3835249 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.3278. Min Act: -0.1700
Data Index: 8725563 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.3278. Min Act: -0.1700
Data Index: 2979567 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.2966. Min Act: -0.1700
Data Index: 5333167 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.2028. Min Act: -0.1700
Data Index: 1856053 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.2028. Min Act: -0.1700
Data Index: 8778649 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.2028. Min Act: -0.1700
Data Index: 8788675 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.2341. Min Act: -0.1700
Data Index: 6322802 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.1716. Min Act: -0.1700
Data Index: 4930294 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.1716. Min Act: -0.1700
Data Index: 8310425 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.2028. Min Act: -0.1700
Data Index: 6139940 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.1403. Min Act: -0.1700
Data Index: 2287637 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.1403. Min Act: -0.1700
Data Index: 1207939 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.1716. Min Act: -0.1700
Data Index: 8596114 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.1091. Min Act: -0.1700
Data Index: 7379327 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.1403. Min Act: -0.1700
Data Index: 6700936 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.1403. Min Act: -0.1700
Data Index: 7577448 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.1091. Min Act: -0.1700
Data Index: 1834012 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.1091. Min Act: -0.1700
Data Index: 2453522 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4216. Min Range: -5.4216
Max Act: 5.1091. Min Act: -0.1700
Data Index: 8382879 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19