Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2208 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.5901. Min Act: -0.1700
Data Index: 7184528 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.5588. Min Act: -0.1700
Data Index: 4583773 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.4338. Min Act: -0.1700
Data Index: 4028308 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.4651. Min Act: -0.1700
Data Index: 2562895 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.3713. Min Act: -0.1700
Data Index: 4865737 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.3088. Min Act: -0.1700
Data Index: 2107509 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.3088. Min Act: -0.1700
Data Index: 6883352 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.3088. Min Act: -0.1700
Data Index: 2077042 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.2776. Min Act: -0.1700
Data Index: 810185 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.2776. Min Act: -0.1700
Data Index: 8282289 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.2776. Min Act: -0.1700
Data Index: 772228 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.2776. Min Act: -0.1700
Data Index: 759047 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.2776. Min Act: -0.1700
Data Index: 7877382 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.2463. Min Act: -0.1700
Data Index: 3536928 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.2776. Min Act: -0.1700
Data Index: 6782184 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.2151. Min Act: -0.1700
Data Index: 7877383 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.2463. Min Act: -0.1700
Data Index: 7877379 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.2463. Min Act: -0.1700
Data Index: 4239891 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.2463. Min Act: -0.1700
Data Index: 449433 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5901. Min Range: -6.5901
Max Act: 6.2776. Min Act: -0.1700
Data Index: 4751789 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19