Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3618 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.6673. Min Act: -0.1700
Data Index: 4530197 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.5735. Min Act: -0.1700
Data Index: 3265727 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.3548. Min Act: -0.1700
Data Index: 6769356 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.3235. Min Act: -0.1700
Data Index: 6952706 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.2298. Min Act: -0.1700
Data Index: 484176 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.1673. Min Act: -0.1700
Data Index: 4303820 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.0735. Min Act: -0.1700
Data Index: 4335579 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.0423. Min Act: -0.1700
Data Index: 1488032 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.0423. Min Act: -0.1700
Data Index: 1206253 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.0423. Min Act: -0.1700
Data Index: 8177706 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.0110. Min Act: -0.1700
Data Index: 1961025 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.0423. Min Act: -0.1700
Data Index: 4174121 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.0110. Min Act: -0.1700
Data Index: 1329312 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6673. Min Range: -6.6673
Max Act: 5.9485. Min Act: -0.1700
Data Index: 5810766 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6673. Min Range: -6.6673
Max Act: 5.9485. Min Act: -0.1700
Data Index: 2563117 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6673. Min Range: -6.6673
Max Act: 5.9173. Min Act: -0.1700
Data Index: 5787002 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6673. Min Range: -6.6673
Max Act: 5.9173. Min Act: -0.1700
Data Index: 4378196 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6673. Min Range: -6.6673
Max Act: 5.9173. Min Act: -0.1700
Data Index: 3039860 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6673. Min Range: -6.6673
Max Act: 5.9173. Min Act: -0.1700
Data Index: 3960644 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6673. Min Range: -6.6673
Max Act: 5.8860. Min Act: -0.1700
Data Index: 6601170 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19