Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 967 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0384. Min Range: -5.0384
Max Act: 5.0384. Min Act: -0.1700
Data Index: 2347608 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.7571. Min Act: -0.1700
Data Index: 4038178 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.7259. Min Act: -0.1700
Data Index: 2835391 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.7259. Min Act: -0.1700
Data Index: 7661156 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.7259. Min Act: -0.1700
Data Index: 5523757 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.6634. Min Act: -0.1700
Data Index: 5778241 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.6321. Min Act: -0.1700
Data Index: 1969734 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.6321. Min Act: -0.1700
Data Index: 5675198 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.6321. Min Act: -0.1700
Data Index: 5119520 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.5696. Min Act: -0.1700
Data Index: 1452429 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.5696. Min Act: -0.1700
Data Index: 4411906 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.6009. Min Act: -0.1700
Data Index: 4070161 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.5384. Min Act: -0.1700
Data Index: 2493075 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.5696. Min Act: -0.1700
Data Index: 602058 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.5696. Min Act: -0.1700
Data Index: 3057941 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.5696. Min Act: -0.1700
Data Index: 2988190 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.5696. Min Act: -0.1700
Data Index: 2157278 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.5384. Min Act: -0.1700
Data Index: 4134013 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.5071. Min Act: -0.1700
Data Index: 3484288 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.5071. Min Act: -0.1700
Data Index: 794968 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19