Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 430 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.3799. Min Act: -0.1700
Data Index: 1357540 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.3799. Min Act: -0.1700
Data Index: 3887429 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.3799. Min Act: -0.1700
Data Index: 1788585 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.3799. Min Act: -0.1700
Data Index: 8743371 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.3799. Min Act: -0.1700
Data Index: 4414120 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.2237. Min Act: -0.1700
Data Index: 3888645 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1612. Min Act: -0.1700
Data Index: 715964 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1612. Min Act: -0.1700
Data Index: 410829 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1299. Min Act: -0.1700
Data Index: 1587086 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1299. Min Act: -0.1700
Data Index: 8364760 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1299. Min Act: -0.1700
Data Index: 3876527 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1299. Min Act: -0.1700
Data Index: 3476212 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1299. Min Act: -0.1700
Data Index: 6763026 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1299. Min Act: -0.1699
Data Index: 853370 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1299. Min Act: -0.1700
Data Index: 5131643 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1299. Min Act: -0.1700
Data Index: 2148741 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.0987. Min Act: -0.1700
Data Index: 795623 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1299. Min Act: -0.1700
Data Index: 4263172 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1299. Min Act: -0.1700
Data Index: 1674019 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.0987. Min Act: -0.1700
Data Index: 1104273 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19