Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1654 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.9524. Min Act: -0.1700
Data Index: 7363435 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.9212. Min Act: -0.1700
Data Index: 4883583 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.8587. Min Act: -0.1700
Data Index: 6078074 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.8899. Min Act: -0.1700
Data Index: 570906 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.7649. Min Act: -0.1700
Data Index: 7453943 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.7649. Min Act: -0.1700
Data Index: 2643869 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.7024. Min Act: -0.1700
Data Index: 8820719 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.6399. Min Act: -0.1700
Data Index: 1232532 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.6399. Min Act: -0.1700
Data Index: 7194328 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.6087. Min Act: -0.1700
Data Index: 1547886 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.6087. Min Act: -0.1700
Data Index: 6363781 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.6087. Min Act: -0.1700
Data Index: 3721204 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.6399. Min Act: -0.1700
Data Index: 1646387 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.5462. Min Act: -0.1700
Data Index: 4581765 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.5462. Min Act: -0.1700
Data Index: 8269001 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.5149. Min Act: -0.1700
Data Index: 7281829 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.5149. Min Act: -0.1700
Data Index: 6653683 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.5462. Min Act: -0.1700
Data Index: 7498326 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.4837. Min Act: -0.1700
Data Index: 1265044 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9524. Min Range: -5.9524
Max Act: 5.4524. Min Act: -0.1700
Data Index: 2740049 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19