Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2343 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.9950. Min Act: -0.1700
Data Index: 959552 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.9013. Min Act: -0.1700
Data Index: 4588173 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.8388. Min Act: -0.1700
Data Index: 8039935 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.7763. Min Act: -0.1700
Data Index: 2101562 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.7450. Min Act: -0.1700
Data Index: 5933085 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.6825. Min Act: -0.1700
Data Index: 8352178 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.5888. Min Act: -0.1700
Data Index: 1415834 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.5575. Min Act: -0.1700
Data Index: 3373684 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.5263. Min Act: -0.1700
Data Index: 10385 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.4950. Min Act: -0.1700
Data Index: 5068093 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.5263. Min Act: -0.1700
Data Index: 4340174 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.4950. Min Act: -0.1700
Data Index: 7697630 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.4950. Min Act: -0.1700
Data Index: 2620132 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.4950. Min Act: -0.1700
Data Index: 2882008 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.4950. Min Act: -0.1700
Data Index: 7584932 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.4638. Min Act: -0.1700
Data Index: 6523514 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.4325. Min Act: -0.1700
Data Index: 6252621 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.4325. Min Act: -0.1700
Data Index: 4210671 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.4325. Min Act: -0.1700
Data Index: 3581953 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9950. Min Range: -5.9950
Max Act: 5.4638. Min Act: -0.1700
Data Index: 4205942 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19