Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1309 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2123. Min Range: -6.2123
Max Act: 6.2123. Min Act: -0.1700
Data Index: 2044407 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2123. Min Range: -6.2123
Max Act: 6.1810. Min Act: -0.1700
Data Index: 1422017 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2123. Min Range: -6.2123
Max Act: 6.1185. Min Act: -0.1700
Data Index: 8671820 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2123. Min Range: -6.2123
Max Act: 6.0873. Min Act: -0.1700
Data Index: 1791103 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2123. Min Range: -6.2123
Max Act: 6.0248. Min Act: -0.1700
Data Index: 6873841 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2123. Min Range: -6.2123
Max Act: 5.9310. Min Act: -0.1700
Data Index: 7362440 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2123. Min Range: -6.2123
Max Act: 5.9623. Min Act: -0.1700
Data Index: 1754247 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2123. Min Range: -6.2123
Max Act: 5.9623. Min Act: -0.1700
Data Index: 348710 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2123. Min Range: -6.2123
Max Act: 5.9310. Min Act: -0.1700
Data Index: 1817888 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2123. Min Range: -6.2123
Max Act: 5.8998. Min Act: -0.1700
Data Index: 8671825 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2123. Min Range: -6.2123
Max Act: 5.9310. Min Act: -0.1700
Data Index: 8566319 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2123. Min Range: -6.2123
Max Act: 5.8998. Min Act: -0.1700
Data Index: 4118172 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2123. Min Range: -6.2123
Max Act: 5.9310. Min Act: -0.1700
Data Index: 1817894 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2123. Min Range: -6.2123
Max Act: 5.8998. Min Act: -0.1700
Data Index: 3955372 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2123. Min Range: -6.2123
Max Act: 5.8998. Min Act: -0.1700
Data Index: 1726233 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2123. Min Range: -6.2123
Max Act: 5.8998. Min Act: -0.1700
Data Index: 7415197 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2123. Min Range: -6.2123
Max Act: 5.8685. Min Act: -0.1700
Data Index: 5724084 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2123. Min Range: -6.2123
Max Act: 5.8685. Min Act: -0.1700
Data Index: 1390852 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2123. Min Range: -6.2123
Max Act: 5.8685. Min Act: -0.1700
Data Index: 8684206 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2123. Min Range: -6.2123
Max Act: 5.8685. Min Act: -0.1700
Data Index: 1817889 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19