Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3593 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2789. Min Range: -7.2789
Max Act: 7.2789. Min Act: -0.1700
Data Index: 3638408 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2789. Min Range: -7.2789
Max Act: 7.2476. Min Act: -0.1700
Data Index: 4669704 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2789. Min Range: -7.2789
Max Act: 7.2164. Min Act: -0.1700
Data Index: 4977777 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2789. Min Range: -7.2789
Max Act: 6.8414. Min Act: -0.1700
Data Index: 2180224 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2789. Min Range: -7.2789
Max Act: 6.6851. Min Act: -0.1700
Data Index: 7192052 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2789. Min Range: -7.2789
Max Act: 6.6226. Min Act: -0.1700
Data Index: 4428634 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2789. Min Range: -7.2789
Max Act: 6.5914. Min Act: -0.1700
Data Index: 665570 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2789. Min Range: -7.2789
Max Act: 6.5601. Min Act: -0.1700
Data Index: 4989619 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2789. Min Range: -7.2789
Max Act: 6.5289. Min Act: -0.1700
Data Index: 417235 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2789. Min Range: -7.2789
Max Act: 6.5289. Min Act: -0.1700
Data Index: 7687445 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2789. Min Range: -7.2789
Max Act: 6.5289. Min Act: -0.1700
Data Index: 3106854 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2789. Min Range: -7.2789
Max Act: 6.4976. Min Act: -0.1700
Data Index: 3667271 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2789. Min Range: -7.2789
Max Act: 6.4976. Min Act: -0.1700
Data Index: 4340511 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2789. Min Range: -7.2789
Max Act: 6.4664. Min Act: -0.1700
Data Index: 3791226 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2789. Min Range: -7.2789
Max Act: 6.4664. Min Act: -0.1700
Data Index: 24448 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2789. Min Range: -7.2789
Max Act: 6.4664. Min Act: -0.1700
Data Index: 2365242 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2789. Min Range: -7.2789
Max Act: 6.4351. Min Act: -0.1700
Data Index: 1356550 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2789. Min Range: -7.2789
Max Act: 6.4351. Min Act: -0.1700
Data Index: 5510596 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2789. Min Range: -7.2789
Max Act: 6.4351. Min Act: -0.1700
Data Index: 5506661 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2789. Min Range: -7.2789
Max Act: 6.3726. Min Act: -0.1700
Data Index: 3631908 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19