Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 70 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.6104. Min Act: -0.1700
Data Index: 6191556 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.5478. Min Act: -0.1700
Data Index: 5571711 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.5165. Min Act: -0.1700
Data Index: 2839386 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.5008. Min Act: -0.1700
Data Index: 8066976 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.5008. Min Act: -0.1700
Data Index: 4057786 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.4851. Min Act: -0.1700
Data Index: 3923620 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.4695. Min Act: -0.1700
Data Index: 6964931 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.4538. Min Act: -0.1700
Data Index: 630045 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.4695. Min Act: -0.1700
Data Index: 6770449 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.4381. Min Act: -0.1700
Data Index: 4620845 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.4381. Min Act: -0.1700
Data Index: 3839415 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.4225. Min Act: -0.1700
Data Index: 4274539 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.3911. Min Act: -0.1700
Data Index: 2093626 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.3911. Min Act: -0.1700
Data Index: 1528783 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.3911. Min Act: -0.1700
Data Index: 2906015 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.3754. Min Act: -0.1700
Data Index: 2264313 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.3754. Min Act: -0.1700
Data Index: 1591100 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.3911. Min Act: -0.1700
Data Index: 5771096 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.3597. Min Act: -0.1700
Data Index: 6770685 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6104. Min Range: -3.6104
Max Act: 3.3597. Min Act: -0.1700
Data Index: 2861115 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19