Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 570 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.9465. Min Act: -0.1700
Data Index: 3015954 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.7590. Min Act: -0.1700
Data Index: 3153783 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.7590. Min Act: -0.1700
Data Index: 1969654 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.6965. Min Act: -0.1700
Data Index: 1061892 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.6340. Min Act: -0.1700
Data Index: 690430 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.6340. Min Act: -0.1700
Data Index: 4039146 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.5715. Min Act: -0.1700
Data Index: 4973614 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.4465. Min Act: -0.1700
Data Index: 2686042 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.4465. Min Act: -0.1700
Data Index: 2506757 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.3840. Min Act: -0.1700
Data Index: 7674070 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.5090. Min Act: -0.1700
Data Index: 7689352 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.4465. Min Act: -0.1700
Data Index: 2024182 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.4465. Min Act: -0.1700
Data Index: 1711419 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.3840. Min Act: -0.1700
Data Index: 1502213 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.3840. Min Act: -0.1700
Data Index: 7394574 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.3840. Min Act: -0.1700
Data Index: 2330280 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.3215. Min Act: -0.1700
Data Index: 900062 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.3840. Min Act: -0.1700
Data Index: 7963653 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.3215. Min Act: -0.1700
Data Index: 5498445 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9465. Min Range: -8.9465
Max Act: 8.2590. Min Act: -0.1700
Data Index: 7560205 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19