Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3432 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0627. Min Range: -5.0627
Max Act: 5.0627. Min Act: -0.1700
Data Index: 7485487 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0627. Min Range: -5.0627
Max Act: 5.0315. Min Act: -0.1700
Data Index: 3390262 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0627. Min Range: -5.0627
Max Act: 4.9377. Min Act: -0.1700
Data Index: 5507235 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0627. Min Range: -5.0627
Max Act: 4.9065. Min Act: -0.1700
Data Index: 980101 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0627. Min Range: -5.0627
Max Act: 4.8752. Min Act: -0.1700
Data Index: 5440331 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0627. Min Range: -5.0627
Max Act: 4.8440. Min Act: -0.1700
Data Index: 1572355 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0627. Min Range: -5.0627
Max Act: 4.8440. Min Act: -0.1700
Data Index: 1988962 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0627. Min Range: -5.0627
Max Act: 4.8127. Min Act: -0.1700
Data Index: 5292703 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0627. Min Range: -5.0627
Max Act: 4.8127. Min Act: -0.1700
Data Index: 7294727 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0627. Min Range: -5.0627
Max Act: 4.7815. Min Act: -0.1700
Data Index: 6137173 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0627. Min Range: -5.0627
Max Act: 4.8127. Min Act: -0.1700
Data Index: 3211406 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0627. Min Range: -5.0627
Max Act: 4.7815. Min Act: -0.1700
Data Index: 7625794 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0627. Min Range: -5.0627
Max Act: 4.7815. Min Act: -0.1700
Data Index: 6446650 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0627. Min Range: -5.0627
Max Act: 4.7815. Min Act: -0.1700
Data Index: 2458317 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0627. Min Range: -5.0627
Max Act: 4.7502. Min Act: -0.1700
Data Index: 6041750 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0627. Min Range: -5.0627
Max Act: 4.7502. Min Act: -0.1700
Data Index: 3359679 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0627. Min Range: -5.0627
Max Act: 4.7190. Min Act: -0.1700
Data Index: 2606024 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0627. Min Range: -5.0627
Max Act: 4.6877. Min Act: -0.1700
Data Index: 4096674 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0627. Min Range: -5.0627
Max Act: 4.6877. Min Act: -0.1700
Data Index: 3253947 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0627. Min Range: -5.0627
Max Act: 4.6877. Min Act: -0.1700
Data Index: 3725486 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19