Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5070 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0383. Min Range: -7.0383
Max Act: 7.0383. Min Act: -0.1700
Data Index: 1780304 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.8508. Min Act: -0.1700
Data Index: 3208423 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.7883. Min Act: -0.1700
Data Index: 940285 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.7883. Min Act: -0.1700
Data Index: 5716027 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.7570. Min Act: -0.1700
Data Index: 466286 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.6633. Min Act: -0.1700
Data Index: 5822983 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.6633. Min Act: -0.1700
Data Index: 2256445 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.6633. Min Act: -0.1700
Data Index: 2109322 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.6008. Min Act: -0.1700
Data Index: 3952456 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.5695. Min Act: -0.1700
Data Index: 3893818 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.5695. Min Act: -0.1700
Data Index: 329681 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.5070. Min Act: -0.1700
Data Index: 3257604 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.5070. Min Act: -0.1700
Data Index: 6542029 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.4758. Min Act: -0.1700
Data Index: 3042258 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.5070. Min Act: -0.1700
Data Index: 174732 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.5070. Min Act: -0.1700
Data Index: 5289009 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.4758. Min Act: -0.1700
Data Index: 8119420 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.4758. Min Act: -0.1700
Data Index: 7380569 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.4445. Min Act: -0.1700
Data Index: 4211057 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0383. Min Range: -7.0383
Max Act: 6.4445. Min Act: -0.1700
Data Index: 4361821 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19