Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3284 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.9669. Min Act: -0.1700
Data Index: 1951419 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.8731. Min Act: -0.1700
Data Index: 2848478 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.8419. Min Act: -0.1700
Data Index: 4378518 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.8419. Min Act: -0.1700
Data Index: 2189702 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.8106. Min Act: -0.1700
Data Index: 8032262 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.8106. Min Act: -0.1700
Data Index: 5423717 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.8106. Min Act: -0.1700
Data Index: 6528088 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.8106. Min Act: -0.1700
Data Index: 3398064 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.7481. Min Act: -0.1700
Data Index: 3226416 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.7169. Min Act: -0.1700
Data Index: 7993563 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.7169. Min Act: -0.1700
Data Index: 71178 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.7169. Min Act: -0.1700
Data Index: 7057034 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.6856. Min Act: -0.1700
Data Index: 8416865 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.6856. Min Act: -0.1700
Data Index: 8043429 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.6544. Min Act: -0.1700
Data Index: 4893038 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.6544. Min Act: -0.1700
Data Index: 3927549 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.6856. Min Act: -0.1700
Data Index: 5539736 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.6544. Min Act: -0.1700
Data Index: 4736383 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.6544. Min Act: -0.1700
Data Index: 7750396 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9669. Min Range: -5.9669
Max Act: 5.6544. Min Act: -0.1700
Data Index: 8081688 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19