Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2892 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.9356. Min Act: -0.1700
Data Index: 3186837 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.9043. Min Act: -0.1700
Data Index: 5888667 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.9043. Min Act: -0.1700
Data Index: 5631430 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.8418. Min Act: -0.1700
Data Index: 697979 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.8106. Min Act: -0.1700
Data Index: 3292419 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.8106. Min Act: -0.1700
Data Index: 7173909 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.7481. Min Act: -0.1700
Data Index: 3749522 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.7168. Min Act: -0.1700
Data Index: 544798 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.6856. Min Act: -0.1700
Data Index: 5243383 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.6856. Min Act: -0.1700
Data Index: 1756107 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.6543. Min Act: -0.1700
Data Index: 4063044 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.6543. Min Act: -0.1700
Data Index: 2818455 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.6543. Min Act: -0.1700
Data Index: 7553544 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.6231. Min Act: -0.1700
Data Index: 322759 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.6231. Min Act: -0.1700
Data Index: 8518684 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.6543. Min Act: -0.1700
Data Index: 8603741 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.5918. Min Act: -0.1700
Data Index: 1033454 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.5918. Min Act: -0.1700
Data Index: 5558810 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.5918. Min Act: -0.1700
Data Index: 786305 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9356. Min Range: -4.9356
Max Act: 4.5606. Min Act: -0.1700
Data Index: 3868632 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19