Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2577 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.6094. Min Act: -0.1700
Data Index: 7789621 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.5157. Min Act: -0.1700
Data Index: 2650351 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.3594. Min Act: -0.1700
Data Index: 3081928 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.3282. Min Act: -0.1700
Data Index: 137181 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.2657. Min Act: -0.1700
Data Index: 3281040 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.2969. Min Act: -0.1700
Data Index: 7870283 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.2657. Min Act: -0.1700
Data Index: 3676230 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.2344. Min Act: -0.1700
Data Index: 8197632 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.2032. Min Act: -0.1700
Data Index: 5763658 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.1407. Min Act: -0.1700
Data Index: 3493468 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.1407. Min Act: -0.1700
Data Index: 1582305 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.1407. Min Act: -0.1700
Data Index: 4919460 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.1407. Min Act: -0.1700
Data Index: 7255409 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.1407. Min Act: -0.1700
Data Index: 809369 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.1407. Min Act: -0.1700
Data Index: 1676607 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.1094. Min Act: -0.1700
Data Index: 2404883 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.0782. Min Act: -0.1700
Data Index: 3920093 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.0782. Min Act: -0.1700
Data Index: 5464402 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.0469. Min Act: -0.1700
Data Index: 5248828 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6094. Min Range: -6.6094
Max Act: 6.0157. Min Act: -0.1700
Data Index: 3656693 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19