Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2836 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.7731. Min Act: -0.1700
Data Index: 8436135 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.7418. Min Act: -0.1700
Data Index: 6851774 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.6481. Min Act: -0.1700
Data Index: 3839202 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.6481. Min Act: -0.1700
Data Index: 1356761 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.5231. Min Act: -0.1700
Data Index: 5854037 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.4606. Min Act: -0.1700
Data Index: 6437415 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.3981. Min Act: -0.1700
Data Index: 5028840 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.2418. Min Act: -0.1700
Data Index: 707242 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.2418. Min Act: -0.1700
Data Index: 6673816 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.2106. Min Act: -0.1700
Data Index: 1091775 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.2106. Min Act: -0.1700
Data Index: 6460368 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.1481. Min Act: -0.1700
Data Index: 3588585 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.1481. Min Act: -0.1700
Data Index: 1117883 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.1168. Min Act: -0.1700
Data Index: 8164530 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.0856. Min Act: -0.1700
Data Index: 7163964 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.0543. Min Act: -0.1700
Data Index: 1334199 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.0543. Min Act: -0.1700
Data Index: 8096151 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.0543. Min Act: -0.1700
Data Index: 564846 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.0543. Min Act: -0.1700
Data Index: 1749695 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7731. Min Range: -7.7731
Max Act: 7.0856. Min Act: -0.1700
Data Index: 1398029 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19