Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 248 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.5820. Min Act: -0.1700
Data Index: 7400433 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.5507. Min Act: -0.1700
Data Index: 5353541 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3632. Min Act: -0.1700
Data Index: 5474130 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3320. Min Act: -0.1700
Data Index: 3475263 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3320. Min Act: -0.1700
Data Index: 5088460 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3007. Min Act: -0.1700
Data Index: 525605 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.2695. Min Act: -0.1700
Data Index: 2554926 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.2382. Min Act: -0.1700
Data Index: 7427833 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.2695. Min Act: -0.1700
Data Index: 5591043 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.2695. Min Act: -0.1700
Data Index: 4752558 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.2695. Min Act: -0.1700
Data Index: 7911982 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.1757. Min Act: -0.1700
Data Index: 2421634 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.2070. Min Act: -0.1700
Data Index: 2169039 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.2070. Min Act: -0.1700
Data Index: 6265728 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.2070. Min Act: -0.1700
Data Index: 6309595 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.2070. Min Act: -0.1700
Data Index: 3820058 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.1132. Min Act: -0.1700
Data Index: 2065988 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.2070. Min Act: -0.1700
Data Index: 8510983 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.1445. Min Act: -0.1700
Data Index: 7194409 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.1445. Min Act: -0.1700
Data Index: 7427423 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19