Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.8805. Min Act: -0.1700
Data Index: 5161262 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.8023. Min Act: -0.1699
Data Index: 2109145 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.7398. Min Act: -0.1700
Data Index: 6185757 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.6616. Min Act: -0.1684
Data Index: 2541684 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.6616. Min Act: -0.1700
Data Index: 668809 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.6146. Min Act: -0.1684
Data Index: 1490495 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.5677. Min Act: -0.1684
Data Index: 2541683 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.5990. Min Act: -0.1700
Data Index: 4368543 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.5833. Min Act: -0.1700
Data Index: 2541691 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.5677. Min Act: -0.1700
Data Index: 5174794 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.5520. Min Act: -0.1700
Data Index: 7405688 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.5207. Min Act: -0.1700
Data Index: 4252701 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.5207. Min Act: -0.1699
Data Index: 1004254 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.5364. Min Act: -0.1700
Data Index: 3661716 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.5050. Min Act: -0.1698
Data Index: 601475 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.5050. Min Act: -0.1684
Data Index: 2541685 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.4580. Min Act: -0.1697
Data Index: 2541665 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.4894. Min Act: -0.1684
Data Index: 2541682 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.4580. Min Act: -0.1692
Data Index: 6337810 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8805. Min Range: -3.8805
Max Act: 3.4737. Min Act: -0.1700
Data Index: 2541678 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19