Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4830 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.5899. Min Act: -0.1700
Data Index: 627710 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.5899. Min Act: -0.1700
Data Index: 5402636 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.5899. Min Act: -0.1700
Data Index: 4278524 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.4649. Min Act: -0.1700
Data Index: 4150373 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.4961. Min Act: -0.1700
Data Index: 537203 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.4336. Min Act: -0.1700
Data Index: 7628758 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.4649. Min Act: -0.1700
Data Index: 604488 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.4024. Min Act: -0.1700
Data Index: 4217906 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.3711. Min Act: -0.1700
Data Index: 6172866 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.3399. Min Act: -0.1700
Data Index: 3507317 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.3399. Min Act: -0.1700
Data Index: 7100426 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.3399. Min Act: -0.1700
Data Index: 6659744 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.3086. Min Act: -0.1700
Data Index: 3210618 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.3711. Min Act: -0.1700
Data Index: 5555958 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.3399. Min Act: -0.1700
Data Index: 4671489 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.3399. Min Act: -0.1700
Data Index: 7658212 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.3086. Min Act: -0.1700
Data Index: 1742318 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.3086. Min Act: -0.1700
Data Index: 2969347 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.3399. Min Act: -0.1700
Data Index: 7480037 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5899. Min Range: -6.5899
Max Act: 6.2774. Min Act: -0.1700
Data Index: 5012106 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19