Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4057 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.7451. Min Act: -0.1700
Data Index: 5972376 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.7138. Min Act: -0.1700
Data Index: 7552914 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.7138. Min Act: -0.1700
Data Index: 8334833 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.7138. Min Act: -0.1700
Data Index: 1348452 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.6513. Min Act: -0.1700
Data Index: 6598554 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.6201. Min Act: -0.1700
Data Index: 579520 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.6201. Min Act: -0.1700
Data Index: 150821 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.5263. Min Act: -0.1700
Data Index: 371244 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.4951. Min Act: -0.1700
Data Index: 1183252 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.4951. Min Act: -0.1700
Data Index: 4059499 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.4638. Min Act: -0.1700
Data Index: 1476349 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.4326. Min Act: -0.1700
Data Index: 8670778 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.4326. Min Act: -0.1700
Data Index: 1091415 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.4013. Min Act: -0.1700
Data Index: 4417069 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.4013. Min Act: -0.1700
Data Index: 1477355 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.4013. Min Act: -0.1700
Data Index: 2675154 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.4013. Min Act: -0.1700
Data Index: 3298674 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.3701. Min Act: -0.1700
Data Index: 3979736 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.3701. Min Act: -0.1700
Data Index: 312286 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7451. Min Range: -5.7451
Max Act: 5.4013. Min Act: -0.1700
Data Index: 6461130 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19