Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2667 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.8669. Min Act: -0.1700
Data Index: 6826336 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.8669. Min Act: -0.1700
Data Index: 6844766 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.8669. Min Act: -0.1700
Data Index: 5310554 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.8044. Min Act: -0.1700
Data Index: 4434100 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.7419. Min Act: -0.1700
Data Index: 6919500 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.7419. Min Act: -0.1700
Data Index: 650248 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.7419. Min Act: -0.1700
Data Index: 1922785 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.7419. Min Act: -0.1700
Data Index: 5411964 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.6794. Min Act: -0.1700
Data Index: 2215821 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.6481. Min Act: -0.1700
Data Index: 3245431 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.6169. Min Act: -0.1700
Data Index: 7097503 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.6169. Min Act: -0.1700
Data Index: 8569367 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.5856. Min Act: -0.1700
Data Index: 4109838 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.5856. Min Act: -0.1700
Data Index: 1927494 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.5856. Min Act: -0.1700
Data Index: 8373124 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.5856. Min Act: -0.1700
Data Index: 4798793 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.5544. Min Act: -0.1700
Data Index: 4205060 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.4919. Min Act: -0.1700
Data Index: 523193 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.5231. Min Act: -0.1700
Data Index: 780583 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8669. Min Range: -5.8669
Max Act: 5.4919. Min Act: -0.1700
Data Index: 688814 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19