Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5403 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.6795. Min Act: -0.1700
Data Index: 2306484 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.6483. Min Act: -0.1700
Data Index: 1354647 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.6170. Min Act: -0.1700
Data Index: 863078 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.5233. Min Act: -0.1700
Data Index: 4519529 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.5233. Min Act: -0.1700
Data Index: 6806445 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.3983. Min Act: -0.1700
Data Index: 136379 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.3670. Min Act: -0.1700
Data Index: 3083750 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.2420. Min Act: -0.1700
Data Index: 3272614 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.2733. Min Act: -0.1688
Data Index: 8096559 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.2108. Min Act: -0.1700
Data Index: 841198 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.2108. Min Act: -0.1700
Data Index: 6806446 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.1795. Min Act: -0.1698
Data Index: 390641 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.2108. Min Act: -0.1700
Data Index: 8114474 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.1483. Min Act: -0.1700
Data Index: 2364215 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.1483. Min Act: -0.1700
Data Index: 4770495 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.0858. Min Act: -0.1700
Data Index: 838998 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.1170. Min Act: -0.1700
Data Index: 8717607 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.1483. Min Act: -0.1700
Data Index: 5170612 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.0858. Min Act: -0.1700
Data Index: 3272613 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.0858. Min Act: -0.1700
Data Index: 2815644 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19