Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4443 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.9365. Min Act: -0.1700
Data Index: 5506642 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.8428. Min Act: -0.1700
Data Index: 6229728 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.8428. Min Act: -0.1700
Data Index: 7338433 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.8115. Min Act: -0.1700
Data Index: 1281369 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.7490. Min Act: -0.1700
Data Index: 1321453 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.7178. Min Act: -0.1700
Data Index: 7002194 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.6865. Min Act: -0.1700
Data Index: 506943 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.6553. Min Act: -0.1700
Data Index: 1011660 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.6553. Min Act: -0.1700
Data Index: 3918835 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.6553. Min Act: -0.1700
Data Index: 7258187 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.6240. Min Act: -0.1700
Data Index: 2914316 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.5928. Min Act: -0.1700
Data Index: 5550695 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.5928. Min Act: -0.1700
Data Index: 7338432 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.5303. Min Act: -0.1700
Data Index: 6286753 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.5303. Min Act: -0.1700
Data Index: 3444079 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.5303. Min Act: -0.1700
Data Index: 2491475 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.4678. Min Act: -0.1700
Data Index: 3410435 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.4990. Min Act: -0.1700
Data Index: 5267343 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.5303. Min Act: -0.1700
Data Index: 4642411 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9365. Min Range: -6.9365
Max Act: 6.5303. Min Act: -0.1700
Data Index: 5012575 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19