Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3040 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.9590. Min Act: -0.1700
Data Index: 4144310 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.9590. Min Act: -0.1700
Data Index: 2718249 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.9590. Min Act: -0.1700
Data Index: 4060883 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.9278. Min Act: -0.1699
Data Index: 7454618 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.9278. Min Act: -0.1700
Data Index: 1776994 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.8965. Min Act: -0.1700
Data Index: 4674957 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.8965. Min Act: -0.1699
Data Index: 448119 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.8653. Min Act: -0.1700
Data Index: 4210477 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.8340. Min Act: -0.1700
Data Index: 8625609 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.8653. Min Act: -0.1700
Data Index: 4353618 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.8340. Min Act: -0.1700
Data Index: 8257438 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.8653. Min Act: -0.1700
Data Index: 621628 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.8653. Min Act: -0.1700
Data Index: 12330 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.8653. Min Act: -0.1700
Data Index: 8168820 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.8340. Min Act: -0.1699
Data Index: 4104403 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.8340. Min Act: -0.1700
Data Index: 6797186 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.8340. Min Act: -0.1699
Data Index: 5802035 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.8340. Min Act: -0.1700
Data Index: 5115397 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.8653. Min Act: -0.1700
Data Index: 2096571 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9590. Min Range: -4.9590
Max Act: 4.8340. Min Act: -0.1700
Data Index: 2151932 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19