Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4084 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.4487. Min Act: -0.1700
Data Index: 4731143 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.4487. Min Act: -0.1700
Data Index: 1767045 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.4487. Min Act: -0.1700
Data Index: 1503256 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.4799. Min Act: -0.1700
Data Index: 6000463 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.3862. Min Act: -0.1700
Data Index: 2673051 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.4174. Min Act: -0.1700
Data Index: 3554342 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.4174. Min Act: -0.1700
Data Index: 4645206 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.3862. Min Act: -0.1700
Data Index: 8422974 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.4174. Min Act: -0.1700
Data Index: 7147648 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.3862. Min Act: -0.1700
Data Index: 417552 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.3549. Min Act: -0.1700
Data Index: 3324661 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.3549. Min Act: -0.1700
Data Index: 6549173 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.3549. Min Act: -0.1700
Data Index: 1472681 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.3237. Min Act: -0.1700
Data Index: 3599787 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.3237. Min Act: -0.1700
Data Index: 6614476 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.3237. Min Act: -0.1700
Data Index: 8738985 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.3237. Min Act: -0.1700
Data Index: 2638715 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.2924. Min Act: -0.1700
Data Index: 128525 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.2612. Min Act: -0.1700
Data Index: 228842 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4799. Min Range: -4.4799
Max Act: 4.2924. Min Act: -0.1700
Data Index: 646847 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19