Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3432 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.7663. Min Act: -0.1700
Data Index: 2596463 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.7038. Min Act: -0.1700
Data Index: 8535091 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.6726. Min Act: -0.1700
Data Index: 6125458 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.5476. Min Act: -0.1700
Data Index: 4123463 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.5788. Min Act: -0.1700
Data Index: 7543813 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.4851. Min Act: -0.1700
Data Index: 8665070 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.4851. Min Act: -0.1700
Data Index: 5024555 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.4851. Min Act: -0.1700
Data Index: 7121251 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.4538. Min Act: -0.1700
Data Index: 403626 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.5163. Min Act: -0.1700
Data Index: 7464333 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.4538. Min Act: -0.1700
Data Index: 2941686 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.4538. Min Act: -0.1700
Data Index: 8734391 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.4538. Min Act: -0.1700
Data Index: 6576927 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.4226. Min Act: -0.1700
Data Index: 4399532 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.4226. Min Act: -0.1700
Data Index: 8183852 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.3913. Min Act: -0.1700
Data Index: 8532583 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.3913. Min Act: -0.1700
Data Index: 6305655 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.3913. Min Act: -0.1700
Data Index: 2618675 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.3601. Min Act: -0.1700
Data Index: 3063971 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7663. Min Range: -5.7663
Max Act: 5.3913. Min Act: -0.1700
Data Index: 3251099 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19