Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3750 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1685. Min Range: -6.1685
Max Act: 6.1685. Min Act: -0.1700
Data Index: 7109359 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1685. Min Range: -6.1685
Max Act: 6.1373. Min Act: -0.1700
Data Index: 2840376 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1685. Min Range: -6.1685
Max Act: 6.1373. Min Act: -0.1700
Data Index: 8477529 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1685. Min Range: -6.1685
Max Act: 6.1060. Min Act: -0.1700
Data Index: 885534 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1685. Min Range: -6.1685
Max Act: 6.0748. Min Act: -0.1700
Data Index: 5002304 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1685. Min Range: -6.1685
Max Act: 6.0435. Min Act: -0.1700
Data Index: 6805234 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1685. Min Range: -6.1685
Max Act: 6.0123. Min Act: -0.1700
Data Index: 5699281 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1685. Min Range: -6.1685
Max Act: 6.0435. Min Act: -0.1700
Data Index: 7213948 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1685. Min Range: -6.1685
Max Act: 6.0123. Min Act: -0.1700
Data Index: 1408807 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1685. Min Range: -6.1685
Max Act: 6.0123. Min Act: -0.1700
Data Index: 5769593 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1685. Min Range: -6.1685
Max Act: 6.0123. Min Act: -0.1700
Data Index: 1771511 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1685. Min Range: -6.1685
Max Act: 6.0123. Min Act: -0.1700
Data Index: 5637499 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1685. Min Range: -6.1685
Max Act: 5.9810. Min Act: -0.1700
Data Index: 1157083 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1685. Min Range: -6.1685
Max Act: 5.9810. Min Act: -0.1700
Data Index: 1604479 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1685. Min Range: -6.1685
Max Act: 5.9810. Min Act: -0.1700
Data Index: 6896472 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1685. Min Range: -6.1685
Max Act: 5.9810. Min Act: -0.1700
Data Index: 8372900 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1685. Min Range: -6.1685
Max Act: 5.9810. Min Act: -0.1700
Data Index: 3180371 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1685. Min Range: -6.1685
Max Act: 5.9185. Min Act: -0.1700
Data Index: 7404689 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1685. Min Range: -6.1685
Max Act: 5.9498. Min Act: -0.1700
Data Index: 3906057 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1685. Min Range: -6.1685
Max Act: 5.9498. Min Act: -0.1700
Data Index: 5264380 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19