Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1438 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0033. Min Range: -6.0033
Max Act: 6.0033. Min Act: -0.1700
Data Index: 2743855 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.9408. Min Act: -0.1700
Data Index: 5648682 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.8470. Min Act: -0.1700
Data Index: 3980876 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.7845. Min Act: -0.1700
Data Index: 6182266 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.7220. Min Act: -0.1700
Data Index: 1834743 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.7220. Min Act: -0.1700
Data Index: 3457068 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.6908. Min Act: -0.1700
Data Index: 2354502 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.7533. Min Act: -0.1700
Data Index: 1240354 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.6595. Min Act: -0.1700
Data Index: 7846393 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.6595. Min Act: -0.1700
Data Index: 916146 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.6283. Min Act: -0.1700
Data Index: 6791007 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.6283. Min Act: -0.1700
Data Index: 2409612 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.6283. Min Act: -0.1700
Data Index: 1248688 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.5970. Min Act: -0.1700
Data Index: 2580640 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.5658. Min Act: -0.1700
Data Index: 3106867 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.5658. Min Act: -0.1700
Data Index: 7746490 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.5658. Min Act: -0.1700
Data Index: 1419211 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.5658. Min Act: -0.1700
Data Index: 4324636 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.5658. Min Act: -0.1700
Data Index: 3980601 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.5345. Min Act: -0.1700
Data Index: 3122288 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19