Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3933 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4048. Min Range: -6.4048
Max Act: 6.4048. Min Act: -0.1700
Data Index: 7767429 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4048. Min Range: -6.4048
Max Act: 6.1861. Min Act: -0.1700
Data Index: 2476770 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4048. Min Range: -6.4048
Max Act: 6.1548. Min Act: -0.1700
Data Index: 3484540 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4048. Min Range: -6.4048
Max Act: 6.0923. Min Act: -0.1700
Data Index: 5497146 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4048. Min Range: -6.4048
Max Act: 5.9986. Min Act: -0.1700
Data Index: 4376011 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4048. Min Range: -6.4048
Max Act: 5.9673. Min Act: -0.1700
Data Index: 4245153 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4048. Min Range: -6.4048
Max Act: 5.9361. Min Act: -0.1700
Data Index: 8775166 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4048. Min Range: -6.4048
Max Act: 5.9673. Min Act: -0.1700
Data Index: 1775221 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4048. Min Range: -6.4048
Max Act: 5.9048. Min Act: -0.1700
Data Index: 6953411 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4048. Min Range: -6.4048
Max Act: 5.8736. Min Act: -0.1700
Data Index: 5370476 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4048. Min Range: -6.4048
Max Act: 5.8736. Min Act: -0.1700
Data Index: 5832484 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4048. Min Range: -6.4048
Max Act: 5.8736. Min Act: -0.1700
Data Index: 3229980 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4048. Min Range: -6.4048
Max Act: 5.8423. Min Act: -0.1700
Data Index: 8617332 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4048. Min Range: -6.4048
Max Act: 5.9048. Min Act: -0.1700
Data Index: 5153245 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4048. Min Range: -6.4048
Max Act: 5.8423. Min Act: -0.1700
Data Index: 82216 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4048. Min Range: -6.4048
Max Act: 5.8423. Min Act: -0.1700
Data Index: 2084346 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4048. Min Range: -6.4048
Max Act: 5.8423. Min Act: -0.1700
Data Index: 6401289 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4048. Min Range: -6.4048
Max Act: 5.8423. Min Act: -0.1700
Data Index: 1718484 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4048. Min Range: -6.4048
Max Act: 5.8111. Min Act: -0.1700
Data Index: 3903630 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4048. Min Range: -6.4048
Max Act: 5.8736. Min Act: -0.1700
Data Index: 3353379 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19