Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3532 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.5986. Min Act: -0.1700
Data Index: 2990775 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.5049. Min Act: -0.1700
Data Index: 4724877 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.3799. Min Act: -0.1700
Data Index: 3167777 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.4111. Min Act: -0.1700
Data Index: 3702646 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.3486. Min Act: -0.1700
Data Index: 5502844 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.2861. Min Act: -0.1700
Data Index: 4926836 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.2549. Min Act: -0.1700
Data Index: 4577408 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.1924. Min Act: -0.1700
Data Index: 7330652 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.2236. Min Act: -0.1700
Data Index: 7437696 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.2236. Min Act: -0.1700
Data Index: 6677111 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.1924. Min Act: -0.1700
Data Index: 5066769 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.1611. Min Act: -0.1700
Data Index: 5726181 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.1611. Min Act: -0.1700
Data Index: 2634995 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.1299. Min Act: -0.1700
Data Index: 78045 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.1611. Min Act: -0.1700
Data Index: 3444056 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.1299. Min Act: -0.1700
Data Index: 8685790 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.1299. Min Act: -0.1700
Data Index: 3275024 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.1299. Min Act: -0.1700
Data Index: 8487043 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.0986. Min Act: -0.1700
Data Index: 3873564 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5986. Min Range: -5.5986
Max Act: 5.0674. Min Act: -0.1700
Data Index: 7091424 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19