Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3061 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.6289. Min Act: -0.1700
Data Index: 4771630 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.5976. Min Act: -0.1700
Data Index: 4110884 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.5351. Min Act: -0.1700
Data Index: 6921758 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.4414. Min Act: -0.1700
Data Index: 1626949 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.3789. Min Act: -0.1700
Data Index: 8267825 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.3789. Min Act: -0.1700
Data Index: 7281611 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.3476. Min Act: -0.1700
Data Index: 4427528 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.3476. Min Act: -0.1700
Data Index: 6662064 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.3476. Min Act: -0.1700
Data Index: 6642588 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.3164. Min Act: -0.1700
Data Index: 3214775 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.3164. Min Act: -0.1700
Data Index: 2180795 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.3164. Min Act: -0.1700
Data Index: 3893759 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.3164. Min Act: -0.1700
Data Index: 5604599 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.2851. Min Act: -0.1700
Data Index: 5230567 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.2851. Min Act: -0.1700
Data Index: 3213413 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.2851. Min Act: -0.1700
Data Index: 5037918 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.2851. Min Act: -0.1700
Data Index: 8442159 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.2851. Min Act: -0.1700
Data Index: 7574163 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.2539. Min Act: -0.1700
Data Index: 6631712 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6289. Min Range: -4.6289
Max Act: 4.2539. Min Act: -0.1700
Data Index: 5779753 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19