Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 729 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0737. Min Range: -4.0737
Max Act: 4.0737. Min Act: -0.1700
Data Index: 2219932 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0737. Min Range: -4.0737
Max Act: 4.0112. Min Act: -0.1700
Data Index: 1758321 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0737. Min Range: -4.0737
Max Act: 4.0112. Min Act: -0.1700
Data Index: 6976402 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0737. Min Range: -4.0737
Max Act: 3.9799. Min Act: -0.1700
Data Index: 3167395 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0737. Min Range: -4.0737
Max Act: 3.9799. Min Act: -0.1700
Data Index: 1409062 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0737. Min Range: -4.0737
Max Act: 3.9799. Min Act: -0.1700
Data Index: 310564 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0737. Min Range: -4.0737
Max Act: 3.9487. Min Act: -0.1700
Data Index: 6771651 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0737. Min Range: -4.0737
Max Act: 3.8862. Min Act: -0.1700
Data Index: 6309221 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0737. Min Range: -4.0737
Max Act: 3.9174. Min Act: -0.1700
Data Index: 8357127 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0737. Min Range: -4.0737
Max Act: 3.8862. Min Act: -0.1700
Data Index: 1032226 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0737. Min Range: -4.0737
Max Act: 3.9174. Min Act: -0.1700
Data Index: 5918429 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0737. Min Range: -4.0737
Max Act: 3.8862. Min Act: -0.1700
Data Index: 409404 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0737. Min Range: -4.0737
Max Act: 3.8862. Min Act: -0.1700
Data Index: 6996067 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0737. Min Range: -4.0737
Max Act: 3.8236. Min Act: -0.1700
Data Index: 5806837 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0737. Min Range: -4.0737
Max Act: 3.8236. Min Act: -0.1700
Data Index: 1029855 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0737. Min Range: -4.0737
Max Act: 3.8549. Min Act: -0.1700
Data Index: 4111485 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0737. Min Range: -4.0737
Max Act: 3.8236. Min Act: -0.1700
Data Index: 310687 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0737. Min Range: -4.0737
Max Act: 3.8549. Min Act: -0.1700
Data Index: 8749719 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0737. Min Range: -4.0737
Max Act: 3.8236. Min Act: -0.1700
Data Index: 370845 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0737. Min Range: -4.0737
Max Act: 3.8236. Min Act: -0.1700
Data Index: 6791903 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19