Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3306 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.5112. Min Act: -0.1700
Data Index: 7861727 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4800. Min Act: -0.1699
Data Index: 4154706 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4487. Min Act: -0.1699
Data Index: 2532954 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4487. Min Act: -0.1692
Data Index: 6438830 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4175. Min Act: -0.1700
Data Index: 2105852 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4487. Min Act: -0.1700
Data Index: 2859042 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4175. Min Act: -0.1695
Data Index: 1980511 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4175. Min Act: -0.1700
Data Index: 4401150 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4175. Min Act: -0.1700
Data Index: 8407914 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3862. Min Act: -0.1700
Data Index: 8274835 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4175. Min Act: -0.1700
Data Index: 8126326 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4487. Min Act: -0.1700
Data Index: 1182664 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4175. Min Act: -0.1700
Data Index: 37987 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4175. Min Act: -0.1700
Data Index: 1118214 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3862. Min Act: -0.1700
Data Index: 3273609 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3862. Min Act: -0.1700
Data Index: 4539490 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3862. Min Act: -0.1700
Data Index: 5098216 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3862. Min Act: -0.1699
Data Index: 5387859 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3862. Min Act: -0.1697
Data Index: 5947235 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3862. Min Act: -0.1700
Data Index: 6568198 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19