Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2745 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.8026. Min Act: -0.1700
Data Index: 2065480 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.6464. Min Act: -0.1700
Data Index: 2417362 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.5526. Min Act: -0.1700
Data Index: 8090400 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.5214. Min Act: -0.1700
Data Index: 7212741 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.4589. Min Act: -0.1700
Data Index: 2259133 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.4589. Min Act: -0.1700
Data Index: 2106641 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.4276. Min Act: -0.1700
Data Index: 739605 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.3964. Min Act: -0.1700
Data Index: 7491476 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.3964. Min Act: -0.1700
Data Index: 1964061 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.3651. Min Act: -0.1700
Data Index: 872973 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.3651. Min Act: -0.1700
Data Index: 2563116 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.3339. Min Act: -0.1700
Data Index: 1830840 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.3026. Min Act: -0.1700
Data Index: 4700441 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.2089. Min Act: -0.1700
Data Index: 2413215 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.2401. Min Act: -0.1700
Data Index: 8605976 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.2401. Min Act: -0.1700
Data Index: 5598437 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.2401. Min Act: -0.1700
Data Index: 4952163 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.2401. Min Act: -0.1700
Data Index: 3050292 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.2401. Min Act: -0.1700
Data Index: 4933022 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8026. Min Range: -6.8026
Max Act: 6.2714. Min Act: -0.1700
Data Index: 33355 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19