Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5529 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0200. Min Range: -5.0200
Max Act: 5.0200. Min Act: -0.1700
Data Index: 141167 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.9575. Min Act: -0.1700
Data Index: 5478496 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.9263. Min Act: -0.1700
Data Index: 2499881 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.8950. Min Act: -0.1700
Data Index: 3175860 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.8638. Min Act: -0.1700
Data Index: 952930 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.8638. Min Act: -0.1700
Data Index: 4968581 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.8013. Min Act: -0.1700
Data Index: 1052416 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.8013. Min Act: -0.1700
Data Index: 382259 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.8013. Min Act: -0.1700
Data Index: 6076107 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.8013. Min Act: -0.1700
Data Index: 805642 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.8325. Min Act: -0.1700
Data Index: 5816387 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.8013. Min Act: -0.1700
Data Index: 2489457 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.7700. Min Act: -0.1700
Data Index: 2798060 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.7388. Min Act: -0.1700
Data Index: 5311828 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.7388. Min Act: -0.1700
Data Index: 4850257 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.7388. Min Act: -0.1700
Data Index: 8433266 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.7075. Min Act: -0.1700
Data Index: 2065956 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.7075. Min Act: -0.1700
Data Index: 1764110 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.7075. Min Act: -0.1700
Data Index: 4213666 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0200. Min Range: -5.0200
Max Act: 4.7388. Min Act: -0.1700
Data Index: 8670426 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19