Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2230 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.9683. Min Act: -0.1700
Data Index: 2574745 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.8121. Min Act: -0.1700
Data Index: 4554371 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.8433. Min Act: -0.1700
Data Index: 748174 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.7496. Min Act: -0.1700
Data Index: 8627809 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.6558. Min Act: -0.1700
Data Index: 2845713 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.6245. Min Act: -0.1700
Data Index: 8067808 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.6245. Min Act: -0.1700
Data Index: 7829824 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.5933. Min Act: -0.1700
Data Index: 2057634 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.5933. Min Act: -0.1700
Data Index: 907127 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.5620. Min Act: -0.1700
Data Index: 5838620 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.6245. Min Act: -0.1700
Data Index: 4641687 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.5620. Min Act: -0.1700
Data Index: 4577635 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.5620. Min Act: -0.1700
Data Index: 6411492 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.5933. Min Act: -0.1700
Data Index: 5360385 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.5933. Min Act: -0.1700
Data Index: 2896097 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.6245. Min Act: -0.1700
Data Index: 2875748 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.5933. Min Act: -0.1700
Data Index: 1061361 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.6245. Min Act: -0.1700
Data Index: 954666 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.5620. Min Act: -0.1700
Data Index: 6948248 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9683. Min Range: -4.9683
Max Act: 4.5933. Min Act: -0.1700
Data Index: 7065460 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19