Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2480 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.6464. Min Act: -0.1700
Data Index: 6261322 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.6151. Min Act: -0.1700
Data Index: 6891976 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.5526. Min Act: -0.1700
Data Index: 965011 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.4589. Min Act: -0.1700
Data Index: 8492594 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.4589. Min Act: -0.1700
Data Index: 3141016 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.4276. Min Act: -0.1700
Data Index: 8267456 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.3964. Min Act: -0.1700
Data Index: 5516332 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.3651. Min Act: -0.1700
Data Index: 2449592 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.3964. Min Act: -0.1700
Data Index: 1195242 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.3651. Min Act: -0.1700
Data Index: 5277246 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.3964. Min Act: -0.1700
Data Index: 1701756 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.3651. Min Act: -0.1700
Data Index: 8476152 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.3651. Min Act: -0.1700
Data Index: 5661878 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.3651. Min Act: -0.1700
Data Index: 2552779 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.3339. Min Act: -0.1700
Data Index: 7368378 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.3651. Min Act: -0.1700
Data Index: 2099455 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.3651. Min Act: -0.1700
Data Index: 4620926 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.3339. Min Act: -0.1700
Data Index: 2308872 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.2714. Min Act: -0.1700
Data Index: 1573797 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6464. Min Range: -6.6464
Max Act: 6.3026. Min Act: -0.1700
Data Index: 77942 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19