Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 975 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.7893. Min Act: -0.1700
Data Index: 717646 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.7893. Min Act: -0.1700
Data Index: 3540371 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.7893. Min Act: -0.1700
Data Index: 8418271 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.7893. Min Act: -0.1700
Data Index: 1665595 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.7580. Min Act: -0.1700
Data Index: 3556024 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.7268. Min Act: -0.1700
Data Index: 7062099 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.7580. Min Act: -0.1700
Data Index: 6446140 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.7268. Min Act: -0.1700
Data Index: 4904143 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.6955. Min Act: -0.1700
Data Index: 1784409 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.6955. Min Act: -0.1700
Data Index: 4656909 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.7268. Min Act: -0.1700
Data Index: 1537975 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.6643. Min Act: -0.1700
Data Index: 6843073 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.6955. Min Act: -0.1700
Data Index: 3065118 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.7268. Min Act: -0.1700
Data Index: 3065120 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.6643. Min Act: -0.1700
Data Index: 2573505 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.6643. Min Act: -0.1700
Data Index: 4957942 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.6643. Min Act: -0.1700
Data Index: 2437812 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.6643. Min Act: -0.1700
Data Index: 763951 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.6330. Min Act: -0.1700
Data Index: 110383 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7893. Min Range: -5.7893
Max Act: 5.6643. Min Act: -0.1700
Data Index: 6768783 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19