Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4274 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4420. Min Range: -4.4420
Max Act: 4.4420. Min Act: -0.1700
Data Index: 1016252 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4420. Min Range: -4.4420
Max Act: 4.2858. Min Act: -0.1700
Data Index: 8047193 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4420. Min Range: -4.4420
Max Act: 4.2858. Min Act: -0.1700
Data Index: 39013 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4420. Min Range: -4.4420
Max Act: 4.2545. Min Act: -0.1700
Data Index: 7323150 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4420. Min Range: -4.4420
Max Act: 4.2232. Min Act: -0.1700
Data Index: 1780320 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4420. Min Range: -4.4420
Max Act: 4.1295. Min Act: -0.1700
Data Index: 8826246 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4420. Min Range: -4.4420
Max Act: 4.0982. Min Act: -0.1700
Data Index: 7810730 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4420. Min Range: -4.4420
Max Act: 4.0982. Min Act: -0.1700
Data Index: 5739525 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4420. Min Range: -4.4420
Max Act: 4.0982. Min Act: -0.1700
Data Index: 190084 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4420. Min Range: -4.4420
Max Act: 4.0982. Min Act: -0.1700
Data Index: 3101159 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4420. Min Range: -4.4420
Max Act: 4.0982. Min Act: -0.1700
Data Index: 6641857 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4420. Min Range: -4.4420
Max Act: 4.0357. Min Act: -0.1700
Data Index: 3727526 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4420. Min Range: -4.4420
Max Act: 4.0982. Min Act: -0.1700
Data Index: 95757 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4420. Min Range: -4.4420
Max Act: 4.0670. Min Act: -0.1700
Data Index: 7191951 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4420. Min Range: -4.4420
Max Act: 4.0670. Min Act: -0.1700
Data Index: 5389288 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4420. Min Range: -4.4420
Max Act: 4.0670. Min Act: -0.1700
Data Index: 2863911 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4420. Min Range: -4.4420
Max Act: 4.0982. Min Act: -0.1700
Data Index: 301931 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4420. Min Range: -4.4420
Max Act: 3.9732. Min Act: -0.1700
Data Index: 618885 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4420. Min Range: -4.4420
Max Act: 3.9732. Min Act: -0.1700
Data Index: 4077013 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4420. Min Range: -4.4420
Max Act: 3.9732. Min Act: -0.1700
Data Index: 8550633 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19